© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 84882
    Prev
    Next
    INDEX
    Explanations

    football team names

    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_23_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
    되지
    0.17
     初始化
    0.16
     Compost
    0.16
     하지
    0.16
    トン
    0.16
    နစ်
    0.15
    缆
    0.15
    茹
    0.15
     επίσης
    0.15
     Late
    0.14
    POSITIVE LOGITS
    Giov
    0.19
    Baltimore
    0.17
    VisualStudio
    0.16
    खी
    0.16
    льного
    0.16
    ியோ
    0.15
    indigo
    0.15
     phosphoric
    0.15
    Glare
    0.15
     vio
    0.15
    Activations Density 0.000%

    No Known Activations