© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 40658
    Prev
    Next
    INDEX
    Explanations

    gravity simulation

    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_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    c
    0.78
    g
    0.77
    r
    0.75
    2
    0.67
    d
    0.67
    t
    0.63
    ре
    0.62
     Maß
    0.60
    lu
    0.60
    b
    0.60
    POSITIVE LOGITS
     ६
    0.70
     for
    0.68
    ו
    0.64
    ן
    0.63
     ८
    0.60
    रोक्त
    0.59
    ीय
    0.59
    ל
    0.58
    ाना
    0.57
    وزیشن
    0.57
    Activations Density 0.001%

    No Known Activations