© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10156
    Prev
    Next
    INDEX
    Explanations

    text describing sporting events, especially wrestling or basketball

    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
    Negative Logits
    AntiForgeryToken
    -0.73
    WEBPACK
    -0.68
    awtextra
    -0.65
     dénon
    -0.63
     FetchType
    -0.62
     Wallflower
    -0.62
    EDEFAULT
    -0.60
    NameInMap
    -0.60
    etcode
    -0.59
    :✨
    -0.58
    POSITIVE LOGITS
     used
    0.49
    RunAsync
    0.48
    used
    0.47
     diman
    0.44
    OGND
    0.44
     التش
    0.44
    </i>
    0.44
    iform
    0.43
     Dor
    0.43
    )|^{
    0.43
    Activations Density 2.414%

    No Known Activations