© 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. 5798
    Prev
    Next
    INDEX
    Explanations

    breaking down complex topics

    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
    مم
    0.64
    nce
    0.61
    ت
    0.61
    poder
    0.61
     synapse
    0.61
    લ
    0.60
    tion
    0.60
    stones
    0.58
    liness
    0.57
    k
    0.57
    POSITIVE LOGITS
    ية
    0.58
    altro
    0.55
     pubblici
    0.55
    ς
    0.54
    िजन
    0.54
     resuscitation
    0.53
    
    0.52
    
    0.52
    iteiten
    0.51
     그래서
    0.51
    Activations Density 0.534%

    No Known Activations