© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12677
    Prev
    Next
    INDEX
    Explanations

    descriptions of soccer plays

    oai_token-act-pair · 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
     betweenstory
    -0.85
    RenderAtEndOf
    -0.82
    */;
    -0.77
    rrggbb
    -0.73
    reportWebVitals
    -0.71
    ,:);
    -0.71
     CreateTagHelper
    -0.69
    ValueStyle
    -0.69
    enumi
    -0.69
    AndEndTag
    -0.67
    POSITIVE LOGITS
     utafiti
    0.43
    رشف
    0.41
     back
    0.40
    ins
    0.39
     bo
    0.37
    tos
    0.37
     
    0.37
     primary
    0.37
     To
    0.36
    WebElementEntity
    0.36
    Activations Density 0.362%

    No Known Activations