© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84648
    Prev
    Next
    INDEX
    Explanations

    Russian and Greek words

    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_0_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
    a
    1.83
    ा
    1.58
    い
    1.48
    你
    1.48
    an
    1.44
    น
    1.41
    ν
    1.37
    া
    1.33
    that
    1.30
    ва
    1.28
    POSITIVE LOGITS
    يان
    1.43
    اتي
    1.41
    cH
    1.41
    ről
    1.36
    лната
    1.35
    urón
    1.34
    cenia
    1.25
    انوي
    1.24
    azgo
    1.24
     staunch
    1.24
    Activations Density 0.000%

    No Known Activations