© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 226494
    Prev
    Next
    INDEX
    Explanations

    Velcro, loop, river

    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_6_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
    ز
    1.48
    ف
    1.27
    on
    1.27
    ad
    1.21
    س
    1.21
    s
    1.13
    ع
    1.13
    ang
    1.12
    د
    1.11
    ap
    1.03
    POSITIVE LOGITS
     namani
    0.99
     CORPER
    0.96
     pourrait
    0.91
     фаразлары
    0.89
     カラ
    0.88
    রি
    0.87
     prodigious
    0.85
     nCenters
    0.84
     povas
    0.84
    <unused2222>
    0.84
    Activations Density 0.000%

    No Known Activations