© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 81268
    Prev
    Next
    INDEX
    Explanations

    acronyms, informal abbreviations, or short forms

    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_31_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
    NeedConnect
    0.40
     luck
    0.39
     चमत्कार
    0.38
    performance
    0.37
    ciaux
    0.37
    草
    0.37
    success
    0.37
    运气
    0.37
     succès
    0.36
    氰
    0.36
    POSITIVE LOGITS
     boja
    0.42
     tooling
    0.41
    ய்
    0.39
     refriger
    0.39
     fitted
    0.39
     contestants
    0.38
    괴
    0.38
    jac
    0.37
    rifft
    0.37
     applicants
    0.35
    Activations Density 0.007%

    No Known Activations