© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 48605
    Prev
    Next
    INDEX
    Explanations

    treat / treating

    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_55_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
    細かい
    0.48
    '\
    0.41
    Pat
    0.41
    Buddy
    0.40
    orme
    0.40
    (`
    0.38
    `/
    0.37
    監査
    0.37
    (`<
    0.37
    Font
    0.36
    POSITIVE LOGITS
     treating
    0.46
     factorización
    0.45
     Treating
    0.44
     treats
    0.43
     treat
    0.42
     traités
    0.42
     hydraul
    0.41
     metaphys
    0.41
    treating
    0.41
     mystic
    0.40
    Activations Density 0.039%

    No Known Activations