© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 129778
    Prev
    Next
    INDEX
    Explanations

    isco sound

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    症
    0.39
    illier
    0.38
    Julie
    0.38
    ulin
    0.36
     ക്
    0.36
    圈
    0.36
     "</
    0.36
     Crunch
    0.35
    웰
    0.35
     lj
    0.35
    POSITIVE LOGITS
    isco
    1.29
     ISC
    1.23
    isc
    1.17
    ISC
    1.17
    ISK
    1.11
    isk
    1.10
    스코
    1.07
    ско
    1.04
    isko
    1.04
    スコ
    1.04
    Activations Density 0.001%

    No Known Activations