© 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. 209695
    Prev
    Next
    INDEX
    Explanations

    Main

    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
    NEGATIVE
    0.38
    Bez
    0.38
     webpages
    0.37
    bez
    0.36
     الاب
    0.35
    })^
    0.35
    ática
    0.35
    امہ
    0.35
     Makita
    0.34
    ᅡ
    0.34
    POSITIVE LOGITS
     Main
    2.63
    Main
    2.38
     main
    1.97
     MAIN
    1.90
    main
    1.89
    MAIN
    1.79
    メイン
    1.53
    getMain
    1.45
     getMain
    1.39
    主
    1.32
    Activations Density 0.002%

    No Known Activations