© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 13089
    Prev
    Next
    INDEX
    Explanations

    source code elements like instructions, labels, and attributes related to compilation and machine learning

    oai_token-act-pair · gemini-2.0-flash

    code/programming

    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
    AntiForgeryToken
    -0.85
    DockStyle
    -0.77
    RenderAtEndOf
    -0.75
     AssemblyCulture
    -0.73
     '\\;'
    -0.70
    rrggbb
    -0.68
     BoxFit
    -0.67
    WritableDatabase
    -0.67
    ThroughAttribute
    -0.66
    zungs
    -0.65
    POSITIVE LOGITS
     الاطلاع
    0.43
     للاسماء
    0.42
    )».
    0.42
    ahalli
    0.40
    se
    0.39
    ブロック
    0.38
    uestamente
    0.37
     विश्वसनीयता
    0.37
     xem
    0.36
    tabPage
    0.36
    Activations Density 2.810%

    No Known Activations