© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8261
    Prev
    Next
    INDEX
    Explanations

    mentions of statistics, scores and results.

    oai_token-act-pair · gemini-2.0-flash

    Numbers and testing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    sequelize
    -0.61
    inflater
    -0.54
    putchar
    -0.50
    Él
    -0.46
    öss
    -0.46
    جمع
    -0.46
    Kanpo
    -0.46
    droje
    -0.45
    mmation
    -0.44
    indole
    -0.44
    POSITIVE LOGITS
    EndInit
    0.67
     wireType
    0.63
     FontWeight
    0.62
     intStringLen
    0.60
    "}")
    0.59
     ")");
    0.57
     "'");
    0.57
    </caption>
    0.57
    ArgsConstructor
    0.56
     Anexo
    0.55
    Activations Density 3.105%

    No Known Activations