© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 63020
    Prev
    Next
    INDEX
    Explanations

    transport

    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_46_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
     public
    2.69
    public
    2.33
     Public
    2.23
    Public
    2.16
     सार्वजनिक
    2.13
     PUBLIC
    2.06
     публи
    1.99
    公
    1.97
     öffentlichen
    1.95
    公共
    1.91
    POSITIVE LOGITS
     Finale
    0.38
    Finale
    0.34
    നായി
    0.34
    orc
    0.34
    ୮
    0.33
    zigzag
    0.33
    peptide
    0.32
     عارف
    0.32
    ინისტრ
    0.32
     irure
    0.32
    Activations Density 0.031%

    No Known Activations