© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 15081
    Prev
    Next
    INDEX
    Explanations

    games like GTA, dwarf, Breath, plants, Diablo

    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
    擊
    0.40
    marshalling
    0.39
    ปลอด
    0.39
    heber
    0.38
    navbarSupported
    0.38
    찰
    0.36
     tragic
    0.36
     செயல்ப
    0.36
     comical
    0.36
    👖
    0.36
    POSITIVE LOGITS
     Minecraft
    0.73
     Multiplayer
    0.68
     Skyrim
    0.67
     Witcher
    0.65
     multiplayer
    0.64
    Minecraft
    0.64
     gameplay
    0.63
     minecraft
    0.61
     Overwatch
    0.61
     Fortnite
    0.60
    Activations Density 0.027%

    No Known Activations