Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 2310
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical and legal terminology, as well as some Russian words

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __":
    
    -0.55
    soever
    -0.55
    __':
    
    -0.54
    %");
    -0.54
     Besøkt
    -0.54
    Beijos
    -0.53
    )");
    
    -0.52
    ImageContext
    -0.51
     WebDriverWait
    -0.49
    expandindo
    -0.49
    POSITIVE LOGITS
    мія
    0.73
    лювання
    0.71
    ліз
    0.65
    кування
    0.64
    лізу
    0.63
    тері
    0.63
    мії
    0.62
    гія
    0.59
    хі
    0.59
     завдання
    0.59
    Activations Density 1.594%

    No Known Activations