© 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
    2. Gemma-3-27B-IT
    3. 41-GEMMASCOPE-2-TRANSCODER-262K
    4. 63676
    Prev
    Next
    INDEX
    Explanations

    synchronization sync synced

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_41_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
    ሸ
    0.42
     Connell
    0.38
    ャ
    0.38
    ട്ടും
    0.37
    اعه
    0.37
    恝
    0.36
     BVHTree
    0.36
     Tertiary
    0.36
     sari
    0.36
    䡒
    0.36
    POSITIVE LOGITS
     synchron
    3.09
     synchronization
    3.06
     synchronize
    2.94
     sincron
    2.94
     синх
    2.91
     synchronized
    2.89
     Synchron
    2.84
     Synchronization
    2.83
     sync
    2.75
    同步
    2.73
    Activations Density 0.008%

    No Known Activations