© 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. 9638
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software configuration and settings

    oai_token-act-pair · gemini-2.0-flash

    configuration

    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
    expandindo
    -1.03
    addContainerGap
    -0.82
    migrationBuilder
    -0.71
    WebServlet
    -0.69
     autorytatywna
    -0.69
    OrNil
    -0.64
     ويكيپيديا
    -0.64
    RTLU
    -0.63
     Bigelow
    -0.62
    SourceChecksum
    -0.61
    POSITIVE LOGITS
    config
    0.85
     config
    0.78
    Config
    0.75
    CONFIG
    0.75
     settings
    0.74
     configuration
    0.74
     Config
    0.73
    Settings
    0.73
    settings
    0.73
    <bos>
    0.71
    Activations Density 1.698%

    No Known Activations