© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 208278
    Prev
    Next
    INDEX
    Explanations

    combinatorial ways

    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_20_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
     पेशकश
    0.49
     শুরুতে
    0.46
     Pardon
    0.44
     Sz
    0.42
    الس
    0.42
    Sz
    0.42
     verdens
    0.41
    岨
    0.41
     konkre
    0.39
    最终
    0.39
    POSITIVE LOGITS
     bàn
    0.46
     quedó
    0.45
     quadrature
    0.40
     `<=
    0.40
     фундамента
    0.40
    鴻
    0.40
    衢
    0.39
    驹
    0.39
     রহিল
    0.38
    냔
    0.38
    Activations Density 0.001%

    No Known Activations