© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 47040
    Prev
    Next
    INDEX
    Explanations

    female names and associated characters

    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_13_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
    š
    0.42
     superficies
    0.37
     Lipschitz
    0.35
     traceability
    0.34
     fenomen
    0.34
     sawtooth
    0.34
     housewives
    0.34
    Resolution
    0.33
     dific
    0.33
    ্স
    0.33
    POSITIVE LOGITS
    𝒃
    0.39
     Christopher
    0.39
    Christopher
    0.39
     لديها
    0.39
     George
    0.36
     Christophe
    0.34
     डॉक्टर
    0.33
     கிறிஸ்து
    0.33
    ියේ
    0.33
     McKay
    0.32
    Activations Density 0.002%

    No Known Activations