© 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. 10341
    Prev
    Next
    INDEX
    Explanations

    Fate/Grand Order

    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
     evening
    0.43
    售
    0.38
    Evening
    0.38
    evening
    0.38
     errors
    0.37
     booted
    0.36
    䛊
    0.36
     Lord
    0.36
     पुरालेखित
    0.36
     removable
    0.36
    POSITIVE LOGITS
     Shortly
    0.39
    흑
    0.38
    ometry
    0.38
     MODULE
    0.36
    MODULE
    0.36
     Ters
    0.36
     модуля
    0.36
     Genel
    0.35
     exped
    0.35
    plemented
    0.35
    Activations Density 0.028%

    No Known Activations