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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5945
    Prev
    Next
    INDEX
    Explanations

    a variety of seemingly unrelated emoji, punctuation, and symbols.

    oai_token-act-pair · gemini-2.0-flash

    representations of affection or emotional connection

    np_token-act-pair-logits · gpt-4o-mini

    emojis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_21/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
    loroethene
    -0.93
     propOrder
    -0.76
    "}")
    -0.66
    říklad
    -0.65
    "}\
    -0.60
    ("}\
    -0.60
    }],
    
    -0.60
    arelli
    -0.59
    endregion
    -0.59
    ']>
    -0.57
    POSITIVE LOGITS
     Roskov
    0.71
    mybatisplus
    0.62
     pinulongan
    0.59
    stateProvider
    0.57
    DoubleQuotes
    0.53
     للاسماء
    0.50
     pleaſure
    0.49
    Искәрмәләр
    0.47
    клопе
    0.46
     neceffary
    0.46
    Activations Density 2.342%

    No Known Activations