© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6548
    Prev
    Next
    INDEX
    Explanations

    the `if __name__ == '__main__'` code block in Python

    oai_token-act-pair · gemini-2.0-flash

    code structure identifiers

    np_token-act-pair-logits · gpt-4o-mini

    Python code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     Cataloging
    -0.48
    DockStyle
    -0.44
    basicConfig
    -0.39
    жка
    -0.38
    ste
    -0.38
    nerie
    -0.38
    ابط
    -0.37
    都好
    -0.37
    <bos>
    -0.36
    ísticas
    -0.36
    POSITIVE LOGITS
    ".
    0.68
    TypedDataSet
    0.67
    konos
    0.65
     MainAxisSize
    0.64
     myſelf
    0.63
    enumi
    0.63
    ربای
    0.62
    ఔ
    0.62
     ModelExpression
    0.62
    tagHelper
    0.61
    Activations Density 0.519%

    No Known Activations