© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 200219
    Prev
    Next
    INDEX
    Explanations

    music fades out

    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_37_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
     পরিচ
    0.40
     কাটিয়ে
    0.39
    หาย
    0.36
    褸
    0.36
    榈
    0.36
     broken
    0.36
    钏
    0.36
     feeds
    0.35
     brushed
    0.35
     honing
    0.35
    POSITIVE LOGITS
     Desa
    0.38
    ශ
    0.38
    insp
    0.38
     Father
    0.38
    mn
    0.37
    overset
    0.37
    oul
    0.36
     Libre
    0.36
     ICH
    0.36
    isher
    0.36
    Activations Density 0.003%

    No Known Activations