© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5881
    Prev
    Next
    INDEX
    Explanations

    happy emojis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    ன
    2.12
    รู้
    2.08
    ว้
    1.99
    l
    1.97
     germination
    1.95
    रा
    1.93
    цкий
    1.90
    
    1.88
    ц
    1.86
    প্তাহ
    1.86
    POSITIVE LOGITS
    
    4.42
    
    2.96
    
    2.96
    
    2.75
    
    2.72
    
    2.71
    
    2.68
    😂😂
    2.67
    েদ
    2.62
    
    2.50
    Activations Density 0.023%

    No Known Activations