© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 132500
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    س
    1.70
    د
    1.51
    ל
    1.51
    ד
    1.37
    ス
    1.35
    ف
    1.27
    大
    1.20
    י
    1.15
    с
    1.11
    ص
    1.09
    POSITIVE LOGITS
     dhe
    0.99
    ation
    0.97
     και
    0.89
    ků
    0.86
    kowe
    0.86
     və
    0.86
     и
    0.85
    và
    0.84
    ker
    0.84
    ки
    0.82
    Activations Density 0.000%

    No Known Activations