© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 113204
    Prev
    Next
    INDEX
    Explanations

    predicting or pre-actions

    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
    t
    1.29
    ма
    1.21
    ↵
    1.20
    ונה
    1.18
    ات
    1.16
    ↵↵
    1.13
    ي
    1.13
    ব
    1.06
    каза
    1.05
    きましょう
    1.05
    POSITIVE LOGITS
    ow
    1.32
    %
    1.18
    你
    1.18
    ರ
    1.09
    ปี
    1.05
    大
    1.05
    ay
    1.05
    وا
    1.05
    You
    1.02
    ור
    1.02
    Activations Density 0.000%

    No Known Activations