© 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. 487
    Prev
    Next
    INDEX
    Explanations

    code-related keywords like 'let', 'case', 'nil', 'storage', 'try', 'using', and other syntax elements.

    oai_token-act-pair · gemini-2.0-flash

    let

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.79
     myſelf
    -0.74
     Numerade
    -0.74
     itſelf
    -0.73
    BeginInit
    -0.71
    RenderAtEndOf
    -0.68
    migrationBuilder
    -0.68
     photolibrary
    -0.68
     getItemId
    -0.68
     makeStyles
    -0.67
    POSITIVE LOGITS
    zeh
    0.52
    htiö
    0.49
    الصفحه
    0.48
    ert
    0.47
    OBJECTIVE
    0.47
    ufen
    0.46
     he
    0.46
    ruitment
    0.45
    ਿੰ
    0.45
    pios
    0.45
    Activations Density 2.703%

    No Known Activations