© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 162740
    Prev
    Next
    INDEX
    Explanations

    virt, step, brand, vid, armor, real, usd, vid

    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_2_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
     renormal
    0.98
    ックス
    0.92
    تری
    0.92
    тна
    0.90
    änder
    0.87
    ᱗
    0.86
    تون
    0.86
     bicovariant
    0.86
    ᱖
    0.86
     Сурикова
    0.85
    POSITIVE LOGITS
    a
    1.97
    in
    1.77
    ا
    1.65
    ه
    1.59
    い
    1.55
    o
    1.48
    ה
    1.46
    া
    1.45
    я
    1.41
    า
    1.41
    Activations Density 0.050%

    No Known Activations