© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 133698
    Prev
    Next
    INDEX
    Explanations

    Arabic and Persian/Urdu characters

    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_37_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
     御
    0.39
    vres
    0.38
     crunchy
    0.37
     evalu
    0.37
    ivasena
    0.37
     arquivo
    0.36
     Vij
    0.35
     =======
    0.35
    っては
    0.35
     resentment
    0.35
    POSITIVE LOGITS
    Practice
    0.36
     เง
    0.36
    เง
    0.36
    Among
    0.36
    updateOne
    0.35
    久
    0.35
    ólnie
    0.35
    dorff
    0.35
    Consequently
    0.34
    ٴ
    0.34
    Activations Density 0.001%

    No Known Activations