© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 36450
    Prev
    Next
    INDEX
    Explanations

    game code and structure

    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
    LuaPush
    0.41
     शत्र
    0.40
     dolar
    0.39
    圧縮
    0.39
     రై
    0.38
     Marken
    0.37
     넣
    0.37
     Utilizamos
    0.37
    陌
    0.36
    抂
    0.36
    POSITIVE LOGITS
    Barn
    0.43
     betting
    0.41
    George
    0.39
     player
    0.39
     winnings
    0.39
    etar
    0.38
     bl
    0.38
    Winners
    0.38
    PlayerData
    0.37
    Player
    0.37
    Activations Density 0.000%

    No Known Activations