© 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-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 3283
    Prev
    Next
    INDEX
    Explanations

    lock synchronization mechanisms

    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_5_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
    ISSION
    0.78
    m
    0.78
    न्नाथ
    0.74
     urin
    0.70
    otre
    0.69
    mie
    0.67
    duplicate
    0.66
    atan
    0.65
    icture
    0.65
    ้
    0.65
    POSITIVE LOGITS
    ┇
    0.74
     Prozess
    0.68
    ζί
    0.67
    𝑵
    0.63
     здоров
    0.62
    ͕
    0.60
    𝕋
    0.58
    当时的
    0.58
     sich
    0.58
     ‫
    0.57
    Activations Density 0.007%

    No Known Activations