© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 34986
    Prev
    Next
    INDEX
    Explanations

    thing

    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_11_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    {
    0.73
    نا
    0.70
    ="
    0.66
    3
    0.64
    7
    0.63
    un
    0.61
     якого
    0.57
    ad
    0.57
    ant
    0.57
    int
    0.55
    POSITIVE LOGITS
    рке
    0.73
    л
    0.67
     aswell
    0.65
    textepsilon
    0.64
    ﻥ
    0.63
     thậm
    0.63
    meyen
    0.62
    ”)
    0.61
     चाहते
    0.61
    𝒕
    0.61
    Activations Density 0.001%

    No Known Activations