© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7232
    Prev
    Next
    INDEX
    Explanations

    wine, grape, rosé, vino, wine, wines, cellar, Cabernet, wineries, terroir

    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_39_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
    branched
    0.45
    NIH
    0.42
    먹
    0.42
     adip
    0.40
    𝓵
    0.40
    Moder
    0.38
    Kris
    0.38
    цией
    0.38
    juč
    0.37
    Ɩ
    0.37
    POSITIVE LOGITS
     wines
    0.65
     cellar
    0.59
     vin
    0.56
     terroir
    0.54
    ワイン
    0.53
     вино
    0.53
     rosé
    0.52
     vinos
    0.52
     wineries
    0.52
     Cabernet
    0.51
    Activations Density 0.034%

    No Known Activations