© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 8202
    Prev
    Next
    INDEX
    Explanations

    periods alone or periods in association with identifiers and numbers, suggesting a focus on file paths, versions, and possibly floating-point numbers in code snippets

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ↵
    -0.76
    )
    -0.70
    <bos>
    -0.66
    te
    -0.63
    WriteLiteral
    -0.61
    ?
    -0.59
    \[
    -0.57
     religieuses
    -0.54
     spéciaux
    -0.53
    ).
    -0.52
    POSITIVE LOGITS
    ")));
    
    1.02
    دانشنامهٔ
    0.91
    ")){
    
    0.89
    '));
    
    0.88
    InjectAttribute
    0.85
    "));
    
    0.85
    }));
    
    0.83
    تقاوى
    0.83
    '){
    
    0.82
    ()));
    
    0.79
    Activations Density 1.516%

    No Known Activations