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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 2118
    Prev
    Next
    INDEX
    Explanations

    information for citations in an academic setting

    oai_token-act-pair · gemini-2.0-flash

    code, websites, research

    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
    .
    -1.18
    。
    -1.09
    ().
    -1.07
    }$.
    -1.06
    ].
    -1.02
    ).
    -1.02
    !
    -1.01
    $.
    -0.98
    %.
    -0.96
    ।
    -0.93
    POSITIVE LOGITS
     GenerationType
    1.13
    StoryboardSegue
    0.97
     nakalista
    0.95
    mybatisplus
    0.93
    LEncoder
    0.93
     الرياضيه
    0.92
     مرئيه
    0.90
     مشين
    0.90
     يتيمه
    0.89
    ✨:
    0.88
    Activations Density 1.486%

    No Known Activations