© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42344
    Prev
    Next
    INDEX
    Explanations

    King's Gambit, Queen's Gambit, bridge

    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_3_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
     juicy
    0.62
     в
    0.57
    x
    0.56
     photospheric
    0.55
    ⓑ
    0.55
     photosynthetic
    0.54
    acd
    0.54
    ҽ
    0.54
    hint
    0.54
     जहाँ
    0.52
    POSITIVE LOGITS
    人
    0.88
    ح
    0.80
    الي
    0.80
    ش
    0.75
    اح
    0.70
    ing
    0.68
     Index
    0.68
    ة
    0.67
    الق
    0.66
    الإ
    0.66
    Activations Density 0.000%

    No Known Activations