© 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. 19255
    Prev
    Next
    INDEX
    Explanations

    Korean place names

    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
     నే
    0.41
     suburb
    0.41
    ))],
    0.40
     suburbs
    0.39
     જાણી
    0.39
     tins
    0.38
    ंजलि
    0.37
    зим
    0.37
     outskirts
    0.36
     wybr
    0.36
    POSITIVE LOGITS
     Trab
    0.39
     Mines
    0.38
    大数据
    0.37
     Whitaker
    0.37
    Baseline
    0.35
     tissus
    0.35
     DataLoader
    0.35
    鞭
    0.35
    HG
    0.35
     Hutchinson
    0.35
    Activations Density 0.023%

    No Known Activations