© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261299
    Prev
    Next
    INDEX
    Explanations

    let me know

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_5_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    с
    1.17
    س
    1.14
    ;
    0.98
     in
    0.95
    ;}
    0.85
    ia
    0.83
    hibit
    0.83
    0
    0.81
    6
    0.80
    fifth
    0.80
    POSITIVE LOGITS
    l
    1.14
    。
    1.12
    ？
    1.10
    、
    0.97
    ！
    0.97
    没有
    0.95
    ，
    0.94
    ν
    0.94
     for
    0.93
    ي
    0.93
    Activations Density 0.001%

    No Known Activations