© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26094
    Prev
    Next
    INDEX
    Explanations

    significant amounts, past, part, hurdle, leak, bad, other, area, number

    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_10_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
     cliché
    0.54
    体验
    0.52
     我们
    0.52
    ３
    0.51
    技术
    0.50
     ㅣ
    0.49
    用户
    0.49
     flavours
    0.49
    但我
    0.49
    但
    0.48
    POSITIVE LOGITS
    on
    0.72
    at
    0.70
    t
    0.68
     on
    0.66
    s
    0.63
    м
    0.62
    re
    0.60
    the
    0.59
    of
    0.56
    л
    0.55
    Activations Density 0.033%

    No Known Activations