© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 12331
    Prev
    Next
    INDEX
    Explanations

    parts of a configuration file

    oai_token-act-pair · gemini-2.0-flash

    Code, XML, data format

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    utches
    -0.57
    anskje
    -0.50
     Ceux
    -0.42
     Ellos
    -0.41
    pantalones
    -0.41
    IntoConstraints
    -0.41
    ốn
    -0.41
     Nasıl
    -0.40
    avyzd
    -0.39
    saida
    -0.39
    POSITIVE LOGITS
     />';
    0.91
    >`;
    0.86
     />";
    0.81
    "]);
    
    0.80
    />";
    0.80
    >';
    
    0.77
    >";
    
    0.77
     />);
    0.77
    :");
    
    0.76
    >");
    
    0.72
    Activations Density 13.346%

    No Known Activations