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. 16-GEMMASCOPE-TRANSCODER-16K
    4. 16359
    Prev
    Next
    INDEX
    Explanations

    code, names, and dates

    oai_token-act-pair · gemini-2.0-flash

    Hungarian words or code

    np_token-act-pair-logits · gemini-2.0-flash

    Mixed languages/identifiers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_16/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
    endphp
    -0.59
    ('');
    
    -0.55
    "]="
    -0.55
    }));
    
    -0.54
    ]";
    -0.54
    |]
    -0.53
    siel
    -0.52
     occupied
    -0.52
    ")),
    -0.50
    "]').
    -0.50
    POSITIVE LOGITS
    sidemargin
    0.76
     Allegretto
    0.62
    OGND
    0.60
     समीक्षाओं
    0.56
    Ҭ
    0.52
     voulons
    0.52
    richTextPanel
    0.52
     الاطلاع
    0.51
    govina
    0.50
    aliyun
    0.49
    Activations Density 0.591%

    No Known Activations