© 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. 2031
    Prev
    Next
    INDEX
    Explanations

    Zootopia, Hyrule, obstacle courses, spell

    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
     ঝামে
    0.40
    敔
    0.39
    魉
    0.37
    ♟
    0.37
     Installed
    0.37
    Installed
    0.36
    美味
    0.35
     月
    0.34
    කාර
    0.34
    ಿಯೂ
    0.34
    POSITIVE LOGITS
     survival
    0.58
     Survival
    0.52
    survival
    0.50
    Survival
    0.49
     supervivencia
    0.49
    生存
    0.47
     soprav
    0.46
     વ
    0.43
     tart
    0.43
     spawn
    0.42
    Activations Density 0.061%

    No Known Activations