© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170205
    Prev
    Next
    INDEX
    Explanations

    artistic director or creative direction

    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_20_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
     conditionals
    0.45
    仕組み
    0.43
    แน่นอน
    0.43
    考察
    0.40
     منظم
    0.39
    course
    0.39
    促进
    0.39
     പക്ഷ
    0.39
    '=>$
    0.38
     நிகழ்ச்ச
    0.38
    POSITIVE LOGITS
     PHOT
    0.45
     poder
    0.43
     Socks
    0.43
     NPCs
    0.43
     sanctuaries
    0.43
    UNIVERS
    0.43
     SPT
    0.43
     sanctuary
    0.42
     trauma
    0.42
     Extracts
    0.42
    Activations Density 0.000%

    No Known Activations