© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 64591
    Prev
    Next
    INDEX
    Explanations

    convex hull

    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_41_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
     Loi
    0.42
    昧
    0.41
     Yankees
    0.38
    ствима
    0.38
    浪
    0.37
    祇
    0.37
    strong
    0.36
     выглядит
    0.36
    味料
    0.36
     STRONG
    0.36
    POSITIVE LOGITS
     convex
    1.64
     Convex
    1.49
    convex
    1.41
     convexity
    1.28
    凸
    1.25
     convexe
    1.18
     convexo
    1.05
     convexes
    0.96
     hull
    0.93
     conv
    0.92
    Activations Density 0.002%

    No Known Activations