© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 135477
    Prev
    Next
    INDEX
    Explanations

    Wadi Rum camping, SOX compliance

    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_6_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
    ي
    1.36
    る
    1.28
    ו
    1.27
     richiesta
    1.21
     زیرمه
    1.09
     funziona
    1.09
     céré
    1.09
     لیګ
    1.08
     کوډ
    1.08
     percentuale
    1.07
    POSITIVE LOGITS
    h
    1.60
    1
    1.54
    0
    1.44
    sl
    1.38
    f
    1.37
    </h2>
    1.34
    s
    1.29
    sc
    1.27
    ne
    1.27
    sh
    1.26
    Activations Density 0.000%

    No Known Activations