© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35809
    Prev
    Next
    INDEX
    Explanations

    fighting sports

    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_11_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
    S
    0.68
    D
    0.60
    MB
    0.60
    RAJ
    0.57
    MS
    0.57
    TB
    0.57
     Asked
    0.56
    K
    0.55
    Templ
    0.55
    ્સ
    0.54
    POSITIVE LOGITS
     becom
    0.54
    ňa
    0.54
    ня
    0.52
     keresztül
    0.49
     около
    0.49
     станови
    0.49
     չ
    0.48
    ecas
    0.48
     znacznie
    0.48
     ။
    0.48
    Activations Density 0.008%

    No Known Activations