© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36915
    Prev
    Next
    INDEX
    Explanations

    granulated sugar

    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_11_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
    examples
    0.49
    奋
    0.46
    া
    0.45
    ম
    0.43
     schoolchildren
    0.42
    データ
    0.42
     exaggerated
    0.42
    न्हे
    0.41
     частини
    0.41
     exemples
    0.40
    POSITIVE LOGITS
     sugar
    0.59
     sugars
    0.56
     dextrose
    0.51
     sucrose
    0.49
     myof
    0.49
    糖
    0.49
     Sugar
    0.48
     fructose
    0.47
     refine
    0.47
     tol
    0.47
    Activations Density 0.071%

    No Known Activations