© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4134
    Prev
    Next
    INDEX
    Explanations

    John KeyFumio KishidaBenjamin NetanyahuYoon Suk-yeolSatya NadellaGabriel BoricQin GangKing Charles III

    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
     فنا
    0.21
    Wrong
    0.20
    ोजा
    0.20
     बराबरी
    0.20
     persamaan
    0.19
     भेद
    0.19
    祛
    0.19
    创始人
    0.19
    勺
    0.19
     규칙
    0.19
    POSITIVE LOGITS
     breaking
    0.22
     supported
    0.19
     Mrs
    0.19
     Mr
    0.19
     Messrs
    0.18
     S
    0.18
     Ir
    0.18
     supp
    0.18
    Ir
    0.18
     Sunny
    0.18
    Activations Density 0.031%

    No Known Activations