© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3504
    Prev
    Next
    INDEX
    Explanations

    terms or phrases surrounded by quotation marks and related to programming code or chemical symbols

    oai_token-act-pair · gemini-2.0-flash

    technical/scientific writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    <bos>
    -0.49
     상세
    -0.48
    matism
    -0.38
     BytesLike
    -0.38
     ge
    -0.37
    országban
    -0.37
     borg
    -0.37
     المل
    -0.37
     rost
    -0.37
    uit
    -0.36
    POSITIVE LOGITS
     itſelf
    0.78
     ſeveral
    0.77
     Majefty
    0.75
    StoryboardSegue
    0.74
     Waray
    0.73
     ſtate
    0.73
     myſelf
    0.72
     Efq
    0.71
     whoſe
    0.71
    %\]
    0.71
    Activations Density 4.136%

    No Known Activations