© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 219597
    Prev
    Next
    INDEX
    Explanations

    arabic culture

    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_47_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
     hosp
    0.41
     हर्षवर्धन
    0.40
     sugli
    0.40
     Chief
    0.38
    OHN
    0.38
    帷
    0.38
     किम
    0.37
    }{*}{
    0.37
    ЗИ
    0.37
    ಿಕ
    0.36
    POSITIVE LOGITS
     Saleh
    0.44
     arabic
    0.43
    阿拉伯
    0.42
     Sharif
    0.42
     hijab
    0.42
     Abubakar
    0.41
    arab
    0.40
     Salah
    0.39
    allah
    0.39
    Keb
    0.39
    Activations Density 0.000%

    No Known Activations