© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 27099
    Prev
    Next
    INDEX
    Explanations

    distinguish between

    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
    ’
    0.97
    i
    0.88
     (
    0.78
     and
    0.77
    ta
    0.73
    ,
    0.73
    q
    0.72
    tt
    0.71
     tal
    0.68
    n
    0.68
    POSITIVE LOGITS
    ای
    1.02
    رمین
    0.99
     وی
    0.93
    量の
    0.91
    ри
    0.91
    لوں
    0.90
    شی
    0.89
    یر
    0.89
     بی
    0.88
    rī
    0.86
    Activations Density 0.026%

    No Known Activations