© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 247341
    Prev
    Next
    INDEX
    Explanations

    . by, . do, . post, . expect, . in, . or

    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_40_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
    链
    0.55
     chain
    0.49
    Chain
    0.46
     Chain
    0.46
     chaîne
    0.46
     CHAIN
    0.43
     chains
    0.43
     ㅛ
    0.41
    チェーン
    0.41
    鏈
    0.40
    POSITIVE LOGITS
    spr
    0.38
    Spr
    0.35
    ccd
    0.34
    erol
    0.33
    moniker
    0.33
    occa
    0.32
     scroll
    0.32
     bodys
    0.32
    immie
    0.32
     النه
    0.32
    Activations Density 0.001%

    No Known Activations