© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 33480
    Prev
    Next
    INDEX
    Explanations

    assignments, questions, tasks

    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_40_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
     Alvar
    0.40
     Notes
    0.39
     NOTES
    0.39
     #(
    0.39
     επισ
    0.37
     स्लाइड्स
    0.37
     ডেলি
    0.37
     opts
    0.36
     worksheets
    0.36
     〢
    0.35
    POSITIVE LOGITS
    netbeans
    0.37
    Cur
    0.34
     entering
    0.34
    Ingrese
    0.34
     pó
    0.34
     ગૃહ
    0.34
     amplitude
    0.33
     trường
    0.33
    adien
    0.33
    gerald
    0.33
    Activations Density 0.000%

    No Known Activations