© 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. 62697
    Prev
    Next
    INDEX
    Explanations

    higher education colleges

    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
     বা
    0.62
    id
    0.59
    /'
    0.59
    at
    0.58
    as
    0.56
     από
    0.56
    ed
    0.55
     για
    0.54
    い
    0.54
     বাড়ি
    0.53
    POSITIVE LOGITS
    ктор
    0.57
    </h3>
    0.54
    Ҡ
    0.50
     absolv
    0.50
    쌀
    0.49
    خبر
    0.48
     Colleges
    0.48
     Removing
    0.48
     colleges
    0.47
     Possible
    0.47
    Activations Density 0.023%

    No Known Activations