© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13234
    Prev
    Next
    INDEX
    Explanations

    program source code and/or report-like documents where people write about something

    oai_token-act-pair · gemini-2.0-flash

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     Batter
    -0.53
    readystatechange
    -0.50
     Foul
    -0.50
    valdi
    -0.49
     Opp
    -0.48
     ByteArray
    -0.48
     Felic
    -0.48
     canyon
    -0.48
    呼
    -0.48
     batt
    -0.47
    POSITIVE LOGITS
     initComponents
    0.84
     مرئيه
    0.72
    PerformLayout
    0.68
    TagHelper
    0.62
    migrationBuilder
    0.60
    Obrázky
    0.59
    tagext
    0.57
     ویکی‌پدیای
    0.56
     CreateTagHelper
    0.55
    ciato
    0.55
    Activations Density 0.938%

    No Known Activations