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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14030
    Prev
    Next
    INDEX
    Explanations

    quantities and units of measure

    oai_token-act-pair · gemini-2.0-flash

    numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/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
    –
    -0.86
     až
    -0.81
    ~
    -0.68
    ~
    -0.66
     sampai
    -0.66
     to
    -0.65
    -£
    -0.65
    -
    -0.64
     الی
    -0.62
    〜
    -0.62
    POSITIVE LOGITS
    +#+#
    0.79
    `;
    
    0.69
    ]--;
    0.63
    })));
    0.61
    hoga
    0.60
    issage
    0.59
    AnimationsModule
    0.59
     strdup
    0.58
    \{\\
    0.57
    ]**
    0.57
    Activations Density 4.102%

    No Known Activations