© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 25017
    Prev
    Next
    INDEX
    Explanations

    business programs

    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_56_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
    manifolds
    0.39
     mij
    0.38
     \%
    0.36
     INTO
    0.36
    FindFirst
    0.36
    𝑠
    0.36
    tension
    0.35
    哝
    0.35
     santo
    0.34
    stid
    0.34
    POSITIVE LOGITS
     Programme
    0.52
     Program
    0.50
     Programs
    0.48
     Programmes
    0.46
     Website
    0.44
     Scheme
    0.43
     Industry
    0.42
     Legislation
    0.42
     Company
    0.42
     Groups
    0.42
    Activations Density 0.100%

    No Known Activations