© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 142304
    Prev
    Next
    INDEX
    Explanations

    keep a

    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_12_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
    オン
    0.61
    ம்
    0.60
    ভৌম
    0.56
    槇
    0.55
    ﻨ
    0.54
     Да
    0.54
    ಒ
    0.52
     Ө
    0.52
     разъ
    0.52
     शक
    0.52
    POSITIVE LOGITS
    бур
    0.59
     sites
    0.52
    ite
    0.50
     site
    0.50
     Wie
    0.50
    <0x80>
    0.49
    '
    0.49
     acta
    0.48
    бка
    0.48
    布
    0.48
    Activations Density 0.001%

    No Known Activations