© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10424
    Prev
    Next
    INDEX
    Explanations

    code or data file snippets, including programming language syntax, file paths, XML-like structures, and function names.

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    PARATUS
    -0.66
    ContentAsync
    -0.63
    }`).
    -0.58
    UrlResolution
    -0.58
    AJAS
    -0.55
    FTFY
    -0.55
    PDATE
    -0.54
    RenderAtEndOf
    -0.54
    APOLIS
    -0.53
    onaceous
    -0.52
    POSITIVE LOGITS
    ex
    0.59
     métallique
    0.57
    Expose
    0.56
     StatefulWidget
    0.56
     rispar
    0.54
    <
    0.54
     Consultez
    0.52
    pak
    0.50
     OnTriggerEnter
    0.49
     Wicidata
    0.49
    Activations Density 15.257%

    No Known Activations