© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 15991
    Prev
    Next
    INDEX
    Explanations

    numbers in scientific notation and within parentheses

    oai_token-act-pair · gemini-2.0-flash

    Numbers and scientific notation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    </h2>
    -2.03
    ")]
    
    -1.88
    ")){
    
    -1.87
    "));
    
    -1.87
    ']
    
    -1.86
    "]];
    -1.85
    ")]
    -1.84
    '])
    
    -1.82
    "]
    
    -1.80
    */
    
    -1.79
    POSITIVE LOGITS
    ългар
    0.36
    unque
    0.32
    ության
    0.31
    밌
    0.31
    ècie
    0.30
    veaux
    0.29
    đu
    0.29
    issional
    0.29
    —“
    0.29
    urazione
    0.29
    Activations Density 3.289%

    No Known Activations