© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 209739
    Prev
    Next
    INDEX
    Explanations

    mono

    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_43_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
    িত্য
    0.36
    冯
    0.36
    硖
    0.35
    ित्र
    0.35
     Farley
    0.35
     бух
    0.34
     கூட்டணிய
    0.34
    姐
    0.34
    дентифика
    0.34
    DropDownItem
    0.34
    POSITIVE LOGITS
     моно
    3.16
     mono
    3.13
     Mono
    2.89
    Mono
    2.78
    mono
    2.75
     monoc
    2.69
     mon
    2.64
     Mon
    2.53
    モノ
    2.53
    mon
    2.52
    Activations Density 0.007%

    No Known Activations