© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1837
    Prev
    Next
    INDEX
    Explanations

    code-related keywords such as "else", assignment operators and parenthesis pairs

    oai_token-act-pair · gemini-2.0-flash

    {

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     محفوظة
    -0.52
     AssemblyCulture
    -0.45
    lové
    -0.45
    OKER
    -0.44
     lentes
    -0.42
    ographiques
    -0.42
    anet
    -0.42
    XO
    -0.42
    لیت
    -0.41
    oracle
    -0.41
    POSITIVE LOGITS
    TagMode
    0.79
     Мексичка
    0.71
    ViewImports
    0.71
    iprot
    0.69
    WebControls
    0.65
    endphp
    0.65
    migrationBuilder
    0.63
    protoimpl
    0.61
    DockStyle
    0.60
    ^(@)
    0.60
    Activations Density 4.411%

    No Known Activations