© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 162763
    Prev
    Next
    INDEX
    Explanations

    kauz, kuhn, kuh, ku, kų

    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_2_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
    ın
    0.95
     опыт
    0.88
    ك
    0.87
    та
    0.87
     Объ
    0.84
    flight
    0.83
    იკ
    0.83
    fficient
    0.82
     తెలియ
    0.82
    eer
    0.79
    POSITIVE LOGITS
    리
    1.49
    に
    1.20
    u
    1.09
    ə
    1.09
    ہ
    1.08
    릭터
    1.04
    د
    1.02
    ੀਆਂ
    1.01
    નુ
    0.96
    ro
    0.95
    Activations Density 0.000%

    No Known Activations