© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 218641
    Prev
    Next
    INDEX
    Explanations

    most popular or promising

    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_16_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
    s
    0.52
    any
    0.51
     анализ
    0.50
    FE
    0.48
    0
    0.48
    VILLE
    0.48
     تحليل
    0.48
    erne
    0.47
    enye
    0.47
    en
    0.47
    POSITIVE LOGITS
     cinéma
    0.46
     rusted
    0.45
    媧
    0.43
    टीसी
    0.42
     Metallica
    0.42
     hérit
    0.42
    "</
    0.42
     jual
    0.42
     ayat
    0.41
    шер
    0.41
    Activations Density 0.000%

    No Known Activations