© 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. 215081
    Prev
    Next
    INDEX
    Explanations

    punctuation before words

    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
    ologue
    0.39
    geek
    0.38
    SanPham
    0.38
    comes
    0.36
    تاح
    0.35
    Inventory
    0.34
    TreeClassifier
    0.33
    ៀ
    0.33
    🎑
    0.33
    duk
    0.33
    POSITIVE LOGITS
     Violence
    0.39
     Rxe
    0.38
    邗
    0.38
     broadband
    0.38
     scattering
    0.37
     Legisl
    0.37
     discontinuous
    0.37
    вала
    0.35
     SupCt
    0.35
    Violence
    0.35
    Activations Density 0.001%

    No Known Activations