© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41237
    Prev
    Next
    INDEX
    Explanations

    multilingual 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_22_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
     Ethan
    0.30
    sic
    0.29
     repeatedly
    0.29
    ulkan
    0.29
     удо
    0.29
    myForm
    0.29
    Supplementary
    0.28
     Edo
    0.28
     Enth
    0.27
     ధ
    0.27
    POSITIVE LOGITS
     hesitate
    0.30
    Hes
    0.29
     wymaga
    0.29
    
    0.28
    リート
    0.27
     sensibilité
    0.27
    路的
    0.27
     sensitivity
    0.27
     explicación
    0.27
     beschäftigen
    0.27
    Activations Density 0.042%

    No Known Activations