© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34383
    Prev
    Next
    INDEX
    Explanations

    ball movement and games

    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_3_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
    ر
    0.80
    м
    0.80
    ર
    0.76
    م
    0.73
    lç
    0.71
    л
    0.71
    ل
    0.70
    های
    0.68
    र
    0.68
    r
    0.68
    POSITIVE LOGITS
    uje
    0.80
     ball
    0.77
    ed
    0.69
    Ball
    0.69
     Ball
    0.68
     balls
    0.68
     ballpark
    0.66
    1
    0.65
    邪
    0.61
    ing
    0.61
    Activations Density 0.043%

    No Known Activations