© 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. 76002
    Prev
    Next
    INDEX
    Explanations

    Japan, football, soccer

    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
     userInfo
    0.44
    userInfo
    0.38
    頹
    0.37
     Debt
    0.37
     SmackDown
    0.37
     Pereira
    0.37
     Orchid
    0.36
    quired
    0.36
     pointB
    0.36
     Extrem
    0.36
    POSITIVE LOGITS
    サッカー
    0.43
     physicality
    0.39
    漕
    0.38
    蜃
    0.38
    加盟
    0.37
    Authors
    0.36
    単位
    0.36
    Physical
    0.36
    作者
    0.36
     caixa
    0.35
    Activations Density 0.001%

    No Known Activations