Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 262119
    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
    =>$
    1.29
    giờ
    1.28
    ]=\
    1.26
    ;'>
    1.25
    
    1.23
    ]'
    1.23
    ื่ม
    1.23
    whel
    1.23
    ]=
    1.23
    ান
    1.23
    POSITIVE LOGITS
     retom
    1.10
     suç
    1.02
     Plus
    0.99
    вая
    0.95
    ح
    0.93
     Productos
    0.92
     Pero
    0.91
    стов
    0.91
     Lakshmi
    0.90
     многое
    0.90
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.