© 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. 17850
    Prev
    Next
    INDEX
    Explanations

    sports balls

    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
    לע
    0.39
    iejsc
    0.38
    符
    0.37
    leve
    0.37
    嬴
    0.36
     дела
    0.36
     dele
    0.35
    Domic
    0.35
    ológ
    0.34
    Behavior
    0.34
    POSITIVE LOGITS
    ball
    1.30
     ball
    1.18
    Ball
    1.13
    BALL
    1.13
    球
    1.05
    ボール
    1.01
    บอล
    0.98
     Ball
    0.94
    balls
    0.91
    बॉल
    0.90
    Activations Density 0.006%

    No Known Activations