© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12717
    Prev
    Next
    INDEX
    Explanations

    URLs and related words such as link and website

    oai_token-act-pair · gemini-2.0-flash

    www

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     كومونز
    -0.72
    contentLoaded
    -0.64
    VersionUID
    -0.61
     ModelExpression
    -0.60
     InputDecoration
    -0.59
    parsedMessage
    -0.58
     الاطلاع
    -0.58
    InjectAttribute
    -0.58
    AsUp
    -0.57
    MLLoader
    -0.56
    POSITIVE LOGITS
     اق
    0.47
    IntoConstraints
    0.47
     вру
    0.47
    ברס
    0.47
    ()?;
    0.47
     stepmother
    0.47
     taste
    0.46
     jacke
    0.46
    клопе
    0.45
    xodo
    0.45
    Activations Density 2.034%

    No Known Activations