© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 4402
    Prev
    Next
    INDEX
    Explanations

    flavor and taste

    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_40_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
     screech
    0.40
    iça
    0.39
     cheered
    0.38
    趁
    0.37
     microscopic
    0.37
     detective
    0.37
    กรณ์
    0.36
     opportun
    0.36
     volutpat
    0.36
     Ghat
    0.35
    POSITIVE LOGITS
     taste
    2.25
    Taste
    2.09
     Taste
    2.03
    taste
    1.93
    味
    1.89
     tastes
    1.88
     맛
    1.88
    맛
    1.81
     tasted
    1.80
     Geschmack
    1.78
    Activations Density 0.257%

    No Known Activations