© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10721
    Prev
    Next
    INDEX
    Explanations

    code snippets and code-related terms, especially those related to React

    oai_token-act-pair · gemini-2.0-flash

    code components

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     copy
    -1.02
     Copy
    -1.01
    Copy
    -0.98
     COPY
    -0.83
    copy
    -0.82
    COPY
    -0.75
     right
    -0.74
     copying
    -0.70
    Right
    -0.70
     copia
    -0.70
    POSITIVE LOGITS
    WriteTagHelper
    0.63
     nahilalakip
    0.61
    DeleteBehavior
    0.61
    enumii
    0.61
    InjectAttribute
    0.59
    endphp
    0.58
    elemField
    0.58
    RenderAtEndOf
    0.57
    LLocation
    0.56
    PCell
    0.55
    Activations Density 1.164%

    No Known Activations