© 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-3-4B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 245939
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_11_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
    আ
    1.50
     imbalances
    1.36
    还有
    1.28
     coils
    1.27
     bottlenecks
    1.27
    টো
    1.23
    А
    1.23
     toasts
    1.22
     accessori
    1.21
     malfunctions
    1.19
    POSITIVE LOGITS
    šit
    1.12
     nedenle
    1.08
    ثير
    1.08
    н
    1.07
    特別な
    1.07
    야
    1.04
     decirlo
    0.99
     Intervals
    0.99
    ordinate
    0.98
     lângă
    0.98
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.