© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15960
    Prev
    Next
    INDEX
    Explanations

    legal and academic jargon

    oai_token-act-pair · gemini-2.0-flash

    expressing opinions/judgements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    tonode
    -0.97
    DockStyle
    -0.96
    +:+
    -0.84
     nahilalakip
    -0.81
    LookAnd
    -0.80
    keyColumn
    -0.80
    RectangleBorder
    -0.79
     تانيه
    -0.79
    ThroughAttribute
    -0.78
    CloseOperation
    -0.77
    POSITIVE LOGITS
    .
    0.75
     even
    0.72
     only
    0.68
     where
    0.57
     Even
    0.56
    ,
    0.56
    even
    0.55
    Even
    0.53
    only
    0.53
     also
    0.52
    Activations Density 6.213%

    No Known Activations