© 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. 6232
    Prev
    Next
    INDEX
    Explanations

    instances of "charge" and related words like "in charge" or "charges" often in a legal or political context.

    oai_token-act-pair · gemini-2.0-flash

    charge

    np_max-act · gemini-2.0-flash

    charge

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    "]);
    
    -0.89
    ='';
    
    -0.85
    "));
    
    -0.83
    **/
    
    -0.82
     ')
    
    -0.81
    ")));
    
    -0.81
    )");
    
    -0.81
    ślę
    -0.79
    `,
    
    -0.77
    "),
    
    -0.76
    POSITIVE LOGITS
    bleshooting
    0.73
     Ceramby
    0.70
     Marcell
    0.60
    ándolos
    0.60
     Mennon
    0.59
     tó
    0.59
    PDT
    0.59
    exitRule
    0.58
    ANCE
    0.57
    portation
    0.57
    Activations Density 1.327%

    No Known Activations