© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 258642
    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
     sicuro
    1.01
    iał
    0.98
     يتع
    0.96
     আদায়
    0.96
    м
    0.96
     sharpening
    0.95
    方が
    0.94
    word
    0.94
    यात्रा
    0.94
    .".,
    0.90
    POSITIVE LOGITS
    fulness
    1.28
     baada
    1.26
     astrolog
    1.24
    BURTS
    1.22
     ক্রমা
    1.21
    <unused2222>
    1.21
    <unused2152>
    1.20
    FProperties
    1.18
     Alicante
    1.18
     excessive
    1.18
    Activations Density 0.000%

    No Known Activations