© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 69376
    Prev
    Next
    INDEX
    Explanations

    drinks

    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_46_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
     tea
    1.15
    Tea
    1.14
     Tea
    1.09
    茶
    1.02
    tea
    0.95
     чай
    0.90
    茶叶
    0.84
     teas
    0.80
     TEA
    0.80
     चाय
    0.78
    POSITIVE LOGITS
     Medicine
    0.43
    ડિયો
    0.41
     MCI
    0.40
    isIn
    0.39
    滲
    0.38
    erode
    0.38
     Ecology
    0.37
    дания
    0.36
     进入
    0.36
    सात
    0.36
    Activations Density 0.003%

    No Known Activations