© 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. 217704
    Prev
    Next
    INDEX
    Explanations

    dating

    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
     isothermal
    0.37
     m
    0.36
    viat
    0.36
    zen
    0.36
     新
    0.36
    zerw
    0.36
    urnama
    0.35
    зе
    0.35
     rua
    0.35
     ম
    0.34
    POSITIVE LOGITS
     Breg
    0.48
     Caes
    0.44
     Mirror
    0.43
     Bres
    0.43
     Ses
    0.42
     bd
    0.42
    martin
    0.42
     bps
    0.42
     Pes
    0.41
     Vegas
    0.41
    Activations Density 0.000%

    No Known Activations