© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54661
    Prev
    Next
    INDEX
    Explanations

    across / between / among / divided / split / share

    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_30_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wicht
    0.37
    《
    0.37
     হয়ত
    0.36
    本质
    0.36
     एड
    0.35
     છ
    0.35
    重視
    0.35
     Каждый
    0.35
    հ
    0.35
    慳
    0.35
    POSITIVE LOGITS
     всех
    0.55
     všech
    0.51
     semua
    0.50
     plusieurs
    0.50
     여러
    0.48
     mehrere
    0.48
     всеми
    0.48
     सभी
    0.47
     trois
    0.47
     mehrerer
    0.46
    Activations Density 0.024%

    No Known Activations