© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 213211
    Prev
    Next
    INDEX
    Explanations

    Are

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_47_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
    Props
    0.38
     hend
    0.38
    امات
    0.38
    ારો
    0.36
    भीर
    0.35
    cola
    0.34
    казать
    0.34
    𓏧
    0.34
    परेटर
    0.33
    вла
    0.33
    POSITIVE LOGITS
     distinctly
    0.45
     wyn
    0.43
     distinct
    0.43
     divisional
    0.41
    ियल
    0.39
    )}_{\
    0.39
     reflex
    0.37
     sculpt
    0.37
     Release
    0.37
    ន្ថ
    0.37
    Activations Density 0.007%

    No Known Activations