© 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. 80484
    Prev
    Next
    INDEX
    Explanations

    football or matches

    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
    瀕
    0.42
    翻
    0.41
     भरतपुर
    0.40
     Crook
    0.39
    hept
    0.38
     पलट
    0.38
     चरित्र
    0.37
     rallied
    0.37
     Finch
    0.37
     indexed
    0.37
    POSITIVE LOGITS
     isolating
    0.38
    Isolated
    0.37
     isolated
    0.37
     탱
    0.35
     hứng
    0.34
     transports
    0.34
     chilling
    0.34
     Isolated
    0.33
    펫
    0.33
    隔離
    0.33
    Activations Density 0.005%

    No Known Activations