© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 38842
    Prev
    Next
    INDEX
    Explanations

    sugar

    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_57_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
     sugar
    1.77
    糖
    1.76
     Sugar
    1.70
    Sugar
    1.67
     sugary
    1.66
     şeker
    1.64
    甜
    1.59
    sugar
    1.58
     candy
    1.54
     sweets
    1.52
    POSITIVE LOGITS
    multer
    0.42
    ША
    0.38
    su
    0.36
     SDA
    0.36
     agon
    0.35
     uds
    0.35
    व्स
    0.34
    佥
    0.34
     NVIC
    0.34
     attaché
    0.34
    Activations Density 0.002%

    No Known Activations