© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6235
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to creative activities and processes involving characters and storytelling, and technical concepts, and also virtual rewards.

    oai_token-act-pair · gemini-2.0-flash

    general topics

    np_max-act-logits · gemini-2.0-flash

    say "prepositions/articles" Method used: 2 — because following tokens are prepositions/articles

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     समीक्षक
    -0.85
     utafitiHapana
    -0.74
    Datuak
    -0.69
    httphttps
    -0.69
    GEBURTSDATUM
    -0.63
     فريبيس
    -0.59
    ScopeManager
    -0.59
     wireType
    -0.59
    findpost
    -0.56
    Initializable
    -0.56
    POSITIVE LOGITS
    <bos>
    0.72
     in
    0.65
     for
    0.63
     when
    0.62
     during
    0.60
     by
    0.57
     via
    0.56
     at
    0.56
    PositiveButton
    0.54
     until
    0.53
    Activations Density 22.140%

    No Known Activations