© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9231
    Prev
    Next
    INDEX
    Explanations

    a variety of phrases relating to abstract concepts like methods or religion.

    oai_token-act-pair · gemini-2.0-flash

    Obstacles or actions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     EconPapers
    -0.93
    IntoConstraints
    -0.77
     незавершена
    -0.76
    icitis
    -0.73
     vPvB
    -0.70
    parsedMessage
    -0.69
     Roskov
    -0.68
    TypedDataSet
    -0.68
    WebElementEntity
    -0.67
     Waray
    -0.66
    POSITIVE LOGITS
    <bos>
    1.29
    omiast
    0.49
    danno
    0.48
    ToLeft
    0.47
     judiciales
    0.47
    *
    0.46
    ’
    0.44
    upaten
    0.44
     tuturor
    0.42
    engertian
    0.41
    Activations Density 1.205%

    No Known Activations