© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 16305
    Prev
    Next
    INDEX
    Explanations

    impacts and hitting actions

    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_40_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
    KEYCODE
    0.41
    outlined
    0.37
    ૯
    0.37
     spliced
    0.36
     نهر
    0.35
     torn
    0.34
     bathed
    0.33
    torn
    0.33
     যায়
    0.33
    Υ
    0.33
    POSITIVE LOGITS
     blows
    0.84
     ضرب
    0.77
     knocks
    0.73
     strikes
    0.71
    打
    0.68
    ضرب
    0.67
    打击
    0.67
     struck
    0.66
     hits
    0.64
    打了
    0.64
    Activations Density 0.091%

    No Known Activations