© 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. 11807
    Prev
    Next
    INDEX
    Explanations

    source code comments which disable linters

    oai_token-act-pair · gemini-2.0-flash

    programming language constructs and annotations

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

    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
    GeneratedMessage
    -0.47
     ***!
    -0.47
    FieldDescriptor
    -0.47
     RDC
    -0.46
    <>());
    -0.45
    ())){
    -0.45
    ็จ
    -0.43
    Xna
    -0.43
    */].
    -0.43
     chapels
    -0.43
    POSITIVE LOGITS
    ArgsConstructor
    0.70
    ADVERTISEMENT
    0.67
    yntaxException
    0.66
     CURIAM
    0.63
    enumi
    0.60
    Hochspringen
    0.59
    himovic
    0.59
    BufferException
    0.59
    regon
    0.55
    getSimpleName
    0.54
    Activations Density 1.037%

    No Known Activations