© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 59071
    Prev
    Next
    INDEX
    Explanations

    milk

    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_59_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
     milk
    2.53
     Milk
    2.47
    Milk
    2.47
    milk
    2.23
     MILK
    2.06
    奶
    1.89
     sữa
    1.88
    乳
    1.87
     दूध
    1.85
     Milch
    1.73
    POSITIVE LOGITS
    spers
    0.40
     අතර
    0.38
    izh
    0.37
    lesque
    0.37
    ovician
    0.36
    ianie
    0.36
    izer
    0.35
    шин
    0.35
    otle
    0.35
    ഢ
    0.35
    Activations Density 0.003%

    No Known Activations