© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 209633
    Prev
    Next
    INDEX
    Explanations

    geographic analysis and breakdowns

    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_25_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
     acom
    0.38
     sizi
    0.37
     dull
    0.36
    entire
    0.36
    ುದು
    0.36
     entire
    0.35
    bursement
    0.34
    餘
    0.34
    mes
    0.33
     ered
    0.33
    POSITIVE LOGITS
    妫
    0.46
    িক্ত
    0.41
     territorios
    0.39
     humanos
    0.38
     lactose
    0.38
     pentes
    0.38
     menutup
    0.38
    ர்களின்
    0.37
     бази
    0.37
     शब्दों
    0.37
    Activations Density 0.002%

    No Known Activations