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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11859
    Prev
    Next
    INDEX
    Explanations

    image width sizing for plots, figures, and diagrams

    oai_token-act-pair · gemini-2.0-flash

    code and data

    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
    SourceChecksum
    -0.60
    zep
    -0.55
    čina
    -0.50
     <",
    -0.50
    hous
    -0.50
     extra
    -0.49
    STRUCTION
    -0.49
    landt
    -0.49
    OfMonth
    -0.49
    gua
    -0.48
    POSITIVE LOGITS
    expandindo
    0.72
    addPreferredGap
    0.68
     المعيارى
    0.68
     שוליים
    0.61
    Referències
    0.56
    ñora
    0.56
    UserScript
    0.55
    addContainerGap
    0.55
    posedge
    0.54
    webElementXpaths
    0.54
    Activations Density 1.744%

    No Known Activations