© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 45924
    Prev
    Next
    INDEX
    Explanations

    **bolded section headers or locations**

    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_10_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
    ک
    1.20
    in
    1.07
    ב
    1.06
    de
    0.99
    ana
    0.90
    ח
    0.89
    가
    0.86
     جدید
    0.85
    ve
    0.84
    ש
    0.84
    POSITIVE LOGITS
    ла
    0.66
    充分
    0.66
    String
    0.59
    ων
    0.58
    所有的
    0.57
    are
    0.55
    u
    0.55
     Refs
    0.54
    ስቃ
    0.54
    助
    0.54
    Activations Density 0.034%

    No Known Activations