© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 234270
    Prev
    Next
    INDEX
    Explanations

    rust

    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_46_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
    یات
    0.38
     Tutt
    0.37
    acca
    0.36
    宵
    0.35
    vo
    0.35
     dismiss
    0.35
    浊
    0.35
     vapor
    0.34
    祥
    0.34
     rub
    0.34
    POSITIVE LOGITS
     leaf
    0.45
    petal
    0.43
     folhas
    0.43
     Leaves
    0.42
     feuilles
    0.42
     листья
    0.42
     foglie
    0.42
     Leaf
    0.41
     leaves
    0.41
    高端
    0.41
    Activations Density 0.001%

    No Known Activations