© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45741
    Prev
    Next
    INDEX
    Explanations

    question mark or informal query

    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_13_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
     do
    0.66
    utta
    0.59
    ramique
    0.59
     पानी
    0.56
    tfine
    0.55
    do
    0.55
     phút
    0.54
    纡
    0.54
     회사
    0.53
    ki
    0.53
    POSITIVE LOGITS
     عن
    0.51
    וק
    0.49
    ומר
    0.46
     गि
    0.44
    简洁
    0.44
     صدر
    0.44
     Moder
    0.43
    الب
    0.43
    Пол
    0.43
     অবি
    0.42
    Activations Density 0.078%

    No Known Activations