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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 50065
    Prev
    Next
    INDEX
    Explanations

    division or fraction separators

    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_31_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
    苾
    0.36
    宵
    0.36
     raindrops
    0.35
     byd
    0.35
    住院
    0.35
    每日
    0.35
     ८
    0.34
     полное
    0.34
     напом
    0.33
     planners
    0.33
    POSITIVE LOGITS
    Industry
    0.43
    업
    0.43
    Con
    0.39
     кон
    0.38
    świet
    0.38
    Herk
    0.38
     칼
    0.38
     Leasing
    0.38
    કારી
    0.37
    ﹒
    0.37
    Activations Density 0.000%

    No Known Activations