© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 6921
    Prev
    Next
    INDEX
    Explanations

    mentions of carbon dioxide in a scientific context

    oai_token-act-pair · gemini-2.0-flash

    CO

    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
     W
    -0.52
     [
    -0.50
     face
    -0.47
     f
    -0.47
    ngrx
    -0.47
     écl
    -0.47
    execSQL
    -0.45
     trương
    -0.45
     Rock
    -0.45
     Public
    -0.45
    POSITIVE LOGITS
     يتيمه
    0.82
    */;
    0.79
    __':
    
    0.71
    />";
    0.71
     **/
    
    0.71
    ()");
    0.70
     beſt
    0.70
     />";
    0.69
    ---*/
    0.68
     */;
    0.68
    Activations Density 1.576%

    No Known Activations