© 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. 12691
    Prev
    Next
    INDEX
    Explanations

    code structures in JavaScript or a similar language

    oai_token-act-pair · 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
     Mag
    -0.62
     e
    -0.59
    ↵↵
    -0.57
     mag
    -0.52
     P
    -0.52
    <eos>
    -0.52
     R
    -0.51
     G
    -0.50
     po
    -0.49
     Q
    -0.49
    POSITIVE LOGITS
    InitVars
    0.97
     myſelf
    0.92
    存于互联网档案馆
    0.92
    principalColumn
    0.91
     raiſ
    0.90
     ſeveral
    0.85
    SequentialGroup
    0.85
    IsContent
    0.82
     whoſe
    0.81
     ſever
    0.81
    Activations Density 1.525%

    No Known Activations