© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9442
    Prev
    Next
    INDEX
    Explanations

    code-related keywords like "import", "__all__", and "load"

    oai_token-act-pair · gemini-2.0-flash

    import

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    import
    -1.15
     للمعارف
    -1.04
     تانيه
    -0.84
    SourceChecksum
    -0.79
    RectangleBorder
    -0.79
     ſch
    -0.76
    ſelf
    -0.74
     ſon
    -0.73
    <bos>
    -0.71
     houſe
    -0.69
    POSITIVE LOGITS
    tonsoft
    0.50
    devise
    0.47
    DoubleQuotes
    0.45
     sit
    0.45
     NotFound
    0.44
    openapi
    0.44
    reibt
    0.43
     setContent
    0.43
    ieuse
    0.43
     ring
    0.43
    Activations Density 1.291%

    No Known Activations