© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 193326
    Prev
    Next
    INDEX
    Explanations

    Amount

    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_27_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
    捞
    0.41
     Conti
    0.39
     Mahan
    0.39
     Katt
    0.39
     expl
    0.38
    िपल
    0.38
     taxas
    0.38
     amazingly
    0.37
     prices
    0.36
     ride
    0.36
    POSITIVE LOGITS
    ئ
    0.39
    注意事项
    0.38
     UIAlert
    0.36
    assertRaises
    0.36
     копи
    0.36
     কপি
    0.36
    三
    0.35
     मांग
    0.35
     COPY
    0.35
    ذ
    0.35
    Activations Density 0.004%

    No Known Activations