© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 69536
    Prev
    Next
    INDEX
    Explanations

    Pokémon name prefixes

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     Perd
    0.44
    setAlignment
    0.42
    人力
    0.41
    хин
    0.39
    センター
    0.38
    축
    0.38
    市民
    0.36
    チップ
    0.36
    erview
    0.35
     brav
    0.35
    POSITIVE LOGITS
    kuu
    0.42
     IIS
    0.41
    AZ
    0.40
     ф
    0.40
    াণী
    0.40
     aph
    0.39
     sourceL
    0.38
    Tank
    0.37
    xq
    0.37
    Antique
    0.37
    Activations Density 0.002%

    No Known Activations