© 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. 37223
    Prev
    Next
    INDEX
    Explanations

    LMSYS Organization

    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
    াশ
    0.49
     Ра
    0.40
     ASC
    0.40
     ash
    0.39
     ಲೋ
    0.38
     Ashram
    0.38
     اشک
    0.38
     اش
    0.37
    浚
    0.36
     Atkinson
    0.36
    POSITIVE LOGITS
    alan
    0.40
    Alan
    0.40
    vern
    0.38
    depends
    0.38
    pera
    0.37
    ptid
    0.37
    resti
    0.37
    oelect
    0.37
    arlin
    0.37
    chen
    0.37
    Activations Density 0.001%

    No Known Activations