© 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. 61206
    Prev
    Next
    INDEX
    Explanations

    yog, yogic, yogurts

    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
    ك
    1.52
    s
    1.33
    '
    1.31
    습니다
    1.28
    은
    1.24
    ка
    1.23
    يد
    1.20
    ક
    1.19
    কে
    1.16
    ς
    1.16
    POSITIVE LOGITS
    1.19
    yn
    1.18
    ו
    1.15
    u
    1.04
    iz
    1.02
    os
    1.01
    ves
    0.95
    od
    0.93
    و
    0.92
    ving
    0.89
    Activations Density 0.000%

    No Known Activations