© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 85438
    Prev
    Next
    INDEX
    Explanations

    first appeared/introduced

    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_18_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
     constituer
    0.45
     permettre
    0.45
    យ៉ាង
    0.43
    㓡
    0.41
    બાદ
    0.41
    lamak
    0.41
     artık
    0.40
     piden
    0.40
     rä
    0.39
    лизация
    0.39
    POSITIVE LOGITS
    мс
    0.45
    隔離
    0.43
    Jordan
    0.42
    ल्स
    0.41
    L
    0.41
    我知道
    0.41
     IS
    0.39
    SS
    0.39
    لي
    0.39
     Marcus
    0.39
    Activations Density 0.002%

    No Known Activations