© 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. 8246
    Prev
    Next
    INDEX
    Explanations

    line breaks in code or documents

    oai_token-act-pair · gemini-2.0-flash

    web pages and code

    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
     незавершена
    -1.02
    IVEREF
    -0.92
     AssemblyCulture
    -0.90
    CodedInputStream
    -0.87
    IntoConstraints
    -0.83
    elemField
    -0.78
    LookAnd
    -0.75
    ptonshire
    -0.75
    uxxxx
    -0.74
    ItemBackground
    -0.73
    POSITIVE LOGITS
    ifoli
    0.43
     Hamp
    0.43
    cuál
    0.41
     Straß
    0.39
    path
    0.39
     kär
    0.38
     ör
    0.37
     chama
    0.37
     fréquence
    0.37
    了吗
    0.36
    Activations Density 0.304%

    No Known Activations