© 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. 216617
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas

    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
    டியா
    0.36
     Dominica
    0.36
    邢
    0.35
    দিনই
    0.35
     могли
    0.34
    cheng
    0.34
    பாவ
    0.34
     Vereinigte
    0.34
     অভিব্যক্তি
    0.33
     दोगुनी
    0.33
    POSITIVE LOGITS
    口腔
    0.38
    㗁
    0.37
     люблю
    0.37
     Сло
    0.36
    厡
    0.36
     dependences
    0.35
    扱う
    0.35
    angar
    0.35
    اکر
    0.35
    getRadius
    0.35
    Activations Density 0.000%

    No Known Activations