© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 260097
    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
    ಛ
    1.10
     harp
    1.07
     Сам
    1.04
     паке
    1.03
    С
    0.96
     戸
    0.94
     গঠিত
    0.94
     כל
    0.93
     ר
    0.93
     Mold
    0.92
    POSITIVE LOGITS
    orems
    1.34
     forgo
    1.27
     पहचानने
    1.27
    Futures
    1.25
    rogens
    1.23
    ت
    1.22
     ulcerative
    1.22
    ાર્થના
    1.21
    耄
    1.20
    inventory
    1.19
    Activations Density 0.000%

    No Known Activations