© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 192374
    Prev
    Next
    INDEX
    Explanations

    property management

    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_4_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
     المجلس
    0.77
    كس
    0.77
     الك
    0.73
     كتاب
    0.71
    ﻛ
    0.71
     براي
    0.70
    𝑮
    0.69
    Jy
    0.68
     سريع
    0.68
    X
    0.68
    POSITIVE LOGITS
     to
    0.91
    ร
    0.89
    س
    0.88
    ن
    0.86
     of
    0.84
    ส
    0.82
    น
    0.82
     It
    0.79
    н
    0.79
    ו
    0.76
    Activations Density 0.016%

    No Known Activations