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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 257085
    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_10_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
     médicale
    1.42
    я
    1.32
    ्ड
    1.28
    باد
    1.27
     musculaire
    1.27
     estadounidense
    1.26
    cısı
    1.24
    тів
    1.22
    ต์
    1.21
    ся
    1.21
    POSITIVE LOGITS
    Activity
    1.17
    DI
    1.06
     सं
    1.03
     नारायण
    1.02
    ksiyon
    1.02
    ro
    1.01
     течение
    1.00
    i
    0.99
     months
    0.98
     class
    0.97
    Activations Density 0.000%

    No Known Activations