© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 208607
    Prev
    Next
    INDEX
    Explanations

    direction, domain, or specific groups

    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_25_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
     yapar
    0.22
    MaxPool
    0.22
     технологий
    0.21
     천
    0.21
    Computer
    0.21
     czyli
    0.21
     السماء
    0.21
     daba
    0.20
     kraj
    0.20
     الكهرب
    0.20
    POSITIVE LOGITS
    瓠
    0.22
    ष्टा
    0.21
    宿舍
    0.21
    剽
    0.21
     थानाध्यक्ष
    0.21
    apeake
    0.20
    ังหวัด
    0.20
     ग्रेटर
    0.20
    蒈
    0.20
    ⓤ
    0.20
    Activations Density 0.003%

    No Known Activations