© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 131379
    Prev
    Next
    INDEX
    Explanations

    NBA Finals MVP

    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_1_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
    ิ
    0.97
     MeOH
    0.95
    yfikacja
    0.94
    凶
    0.90
    ası
    0.87
    ahh
    0.87
    르
    0.86
    ાર
    0.86
     trifling
    0.86
     başlat
    0.85
    POSITIVE LOGITS
     to
    1.42
     =
    1.29
     are
    1.25
    ون
    1.25
     of
    1.18
    to
    1.15
    ను
    1.14
    ش
    1.13
     from
    1.10
     و
    1.09
    Activations Density 0.000%

    No Known Activations