© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 199833
    Prev
    Next
    INDEX
    Explanations

    deadlock, mixture, events

    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_27_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
    közi
    0.46
    kreis
    0.44
    élim
    0.44
    kelijk
    0.43
    acelet
    0.41
     אי
    0.41
    Ᏻ
    0.41
     কয়েকটি
    0.40
     озеро
    0.40
    <unused227>
    0.40
    POSITIVE LOGITS
     powered
    0.42
     White
    0.40
     Finance
    0.39
     Culture
    0.37
     care
    0.37
     Riverside
    0.36
     Fin
    0.36
     thicker
    0.36
     learning
    0.35
     culture
    0.35
    Activations Density 0.088%

    No Known Activations