© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 216851
    Prev
    Next
    INDEX
    Explanations

    MV models and TX codes

    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_16_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
    ária
    0.54
     चयनित
    0.54
     เน
    0.53
     fárm
    0.52
    pekte
    0.52
     對
    0.52
     роста
    0.52
     ਦਵਾਈ
    0.52
    ónde
    0.51
     시험
    0.50
    POSITIVE LOGITS
    2
    0.45
    кон
    0.45
     Cutter
    0.45
     Adder
    0.45
    ساب
    0.44
    در
    0.44
     Tea
    0.44
     Tut
    0.44
     had
    0.43
    सद
    0.43
    Activations Density 0.000%

    No Known Activations