© 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. 246970
    Prev
    Next
    INDEX
    Explanations

    Unity C# player/character movement class

    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
     anim
    0.54
     анима
    0.48
     animations
    0.47
     animation
    0.45
     animator
    0.42
    动画
    0.39
    앰
    0.39
    animation
    0.39
     Anim
    0.39
     animados
    0.39
    POSITIVE LOGITS
    শির
    0.43
    カ
    0.41
    オリン
    0.40
     செல்க
    0.39
    Indexes
    0.39
    >/</
    0.38
    Olymp
    0.38
    iflora
    0.38
    ழுகு
    0.38
    Network
    0.37
    Activations Density 0.001%

    No Known Activations