© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6007
    Prev
    Next
    INDEX
    Explanations

    nouns and descriptive verbs, particularly in titles

    oai_token-act-pair · gemini-2.0-flash

    Business/Financial Articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    A
    -0.48
    There
    -0.46
    достатки
    -0.42
    visející
    -0.42
     slutt
    -0.41
     commerciali
    -0.41
    Provide
    -0.41
    duled
    -0.41
    Celebrate
    -0.41
    At
    -0.40
    POSITIVE LOGITS
    yet
    0.43
    TouchListener
    0.40
    ﴿
    0.40
    SuppressMessage
    0.40
    +#+#
    0.39
     onView
    0.39
    mache
    0.38
    ank
    0.37
    not
    0.37
     nakalista
    0.37
    Activations Density 2.984%

    No Known Activations