© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78311
    Prev
    Next
    INDEX
    Explanations

    Colombia

    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_0_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
    the
    2.58
    س
    2.28
    و
    2.19
    م
    2.16
    ম
    2.02
    ס
    1.94
    ן
    1.94
    ن
    1.91
    ו
    1.88
     the
    1.88
    POSITIVE LOGITS
    يد
    1.34
    ется
    1.13
    િન
    1.09
    ňuje
    1.09
    ፈላጊ
    1.08
    iş
    1.07
    λης
    1.06
    ир
    1.04
     Показа
    1.03
    િમ
    1.02
    Activations Density 0.000%

    No Known Activations