© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4327
    Prev
    Next
    INDEX
    Explanations

    code-related snippets with array indexing and math symbols

    oai_token-act-pair · gemini-2.0-flash

    say "special symbols"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     للمعارف
    -0.99
    [
    -0.75
    новништво
    -0.67
     Diakses
    -0.65
    بوابة
    -0.62
    Билгалдахарш
    -0.61
     &[
    -0.61
     >=",
    -0.61
    saraba
    -0.60
    ThroughAttribute
    -0.60
    POSITIVE LOGITS
     se
    0.64
    se
    0.59
     Se
    0.54
    Se
    0.53
     man
    0.53
    SE
    0.48
     mans
    0.46
    GIN
    0.46
    inique
    0.43
    mans
    0.43
    Activations Density 1.148%

    No Known Activations