© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3326
    Prev
    Next
    INDEX
    Explanations

    mechanical details, devices, and functions

    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
    朓
    0.86
    uyết
    0.85
     боль
    0.84
     vini
    0.83
    ydı
    0.81
     puse
    0.80
    푠
    0.79
     truk
    0.78
    ییر
    0.78
     atti
    0.76
    POSITIVE LOGITS
    на
    0.94
     gears
    0.86
    constexpr
    0.79
    न
    0.79
    en
    0.78
    monary
    0.77
    ेच्छा
    0.76
    ℓ
    0.75
    ন
    0.74
     epsilon
    0.73
    Activations Density 0.015%

    No Known Activations