© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 167790
    Prev
    Next
    INDEX
    Explanations

    breakdown by category

    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_31_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
     मीनिंग
    0.40
    nest
    0.39
    Containing
    0.38
    __)
    0.38
     Pip
    0.38
    Dougall
    0.38
     vật
    0.37
    숨
    0.37
    ҳи
    0.37
    kep
    0.37
    POSITIVE LOGITS
    ංශ
    0.40
    淸
    0.37
     MID
    0.36
    ランド
    0.36
     representan
    0.34
    ocentric
    0.33
     सेंट्रल
    0.33
     бен
    0.32
    暌
    0.32
    وى
    0.32
    Activations Density 0.000%

    No Known Activations