© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 154328
    Prev
    Next
    INDEX
    Explanations

    True

    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_23_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
    허
    0.43
    加拿
    0.40
    潼
    0.40
    重新
    0.39
    軖
    0.38
    ത്വ
    0.38
     vectơ
    0.38
    逐
    0.38
     এসেছিল
    0.37
    刘
    0.37
    POSITIVE LOGITS
    denum
    0.43
    詳しい
    0.43
     Projection
    0.39
     entree
    0.38
     läng
    0.37
     ел
    0.37
     v
    0.36
     Vita
    0.35
     yaklaşık
    0.35
    od
    0.35
    Activations Density 0.001%

    No Known Activations