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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43564
    Prev
    Next
    INDEX
    Explanations

    perfumery or perfumed

    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_3_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
    kannya
    1.09
    다
    0.94
    in
    0.82
    '
    0.81
    kamer
    0.80
    k
    0.79
    ti
    0.77
    kker
    0.77
    té
    0.77
    t
    0.77
    POSITIVE LOGITS
     (
    0.79
    il
    0.75
     trifling
    0.73
    ной
    0.66
    ى
    0.66
    ρι
    0.66
     ricos
    0.66
     crouching
    0.65
    т
    0.65
    ikult
    0.62
    Activations Density 0.000%

    No Known Activations