© 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. 41025
    Prev
    Next
    INDEX
    Explanations

    threatened or challenged

    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
     SOAP
    0.39
     통합
    0.38
     مراحل
    0.37
     influ
    0.37
     हस्ता
    0.36
    odik
    0.36
    тік
    0.36
    स्थान
    0.35
     효과
    0.35
    逢
    0.35
    POSITIVE LOGITS
    against
    0.36
     against
    0.35
    瞅
    0.35
     Vaccine
    0.35
     claimed
    0.34
     concentrated
    0.34
     doing
    0.34
    竟然
    0.34
    ్రు
    0.34
     captivity
    0.34
    Activations Density 0.034%

    No Known Activations