© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 226
    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_2_width_16k_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
    り
    2.15
    ्तिक
    1.92
    र
    1.88
    в
    1.75
    ت
    1.72
    т
    1.69
    एं
    1.69
    spaper
    1.68
    一方面
    1.65
    साइटी
    1.63
    POSITIVE LOGITS
    
    1.86
    -\
    1.68
     notables
    1.64
     počet
    1.62
     exons
    1.61
    
    1.61
     eens
    1.57
    ajouter
    1.55
     outp
    1.55
     teren
    1.55
    Activations Density 0.020%

    No Known Activations