© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 139935
    Prev
    Next
    INDEX
    Explanations

    alcohol content and price

    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_37_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cocktail
    1.42
     cocktails
    1.41
     коктей
    1.30
     Cocktail
    1.24
    🍸
    0.95
    Cock
    0.92
    칵
    0.88
     Cock
    0.86
    🍹
    0.86
    cock
    0.81
    POSITIVE LOGITS
    钨
    0.39
    hept
    0.38
     tabloid
    0.38
     heli
    0.36
     piv
    0.36
    adopt
    0.36
    ान्य
    0.35
     tapp
    0.35
    uldu
    0.35
    Coref
    0.35
    Activations Density 0.011%

    No Known Activations