© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 58975
    Prev
    Next
    INDEX
    Explanations

    grossly, grossing, gross

    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_2_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
    1.25
    a
    1.15
    c
    1.08
    া
    1.05
    ا
    1.01
    ה
    0.95
    ור
    0.91
    ע
    0.89
    ാ
    0.89
    ס
    0.88
    POSITIVE LOGITS
    ση
    1.23
    ње
    1.16
    ۵
    1.13
    kých
    1.09
    際に
    1.07
    ール
    1.04
     foli
    1.04
    acija
    1.04
     пять
    1.02
    트
    1.02
    Activations Density 0.003%

    No Known Activations