© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 40583
    Prev
    Next
    INDEX
    Explanations

    encryption ciphers

    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_57_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
    Florida
    0.42
    can
    0.42
    molecule
    0.41
    Wisconsin
    0.41
    SAS
    0.40
    Coll
    0.39
    Colorado
    0.39
    concert
    0.39
    SAP
    0.39
    푐
    0.39
    POSITIVE LOGITS
     спец
    0.42
     dificuldade
    0.40
     NATURAL
    0.39
     Anci
    0.39
    ibu
    0.38
    ofs
    0.38
     o
    0.38
     od
    0.38
     জীবনে
    0.37
     vergang
    0.37
    Activations Density 0.001%

    No Known Activations