© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 51211
    Prev
    Next
    INDEX
    Explanations

    Guilty Gear, Yukino, Battleship

    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_31_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
    侔
    0.40
    брь
    0.38
    鬚
    0.37
     Rostock
    0.36
     bước
    0.36
     далее
    0.36
     Олимпий
    0.36
    逍
    0.35
     должен
    0.35
    GRAM
    0.35
    POSITIVE LOGITS
     কাহার
    0.39
     liquidity
    0.39
     hero
    0.39
     Hagan
    0.38
    undance
    0.38
    FindingsResponse
    0.38
     Buj
    0.38
     battaglia
    0.38
    icus
    0.37
    FindingsRequest
    0.37
    Activations Density 0.061%

    No Known Activations