© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24640
    Prev
    Next
    INDEX
    Explanations

    create visual images

    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_10_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
    '
    0.35
     pertanian
    0.28
    ')
    0.27
     inden
    0.26
     televisi
    0.26
    ă
    0.26
     से
    0.26
     dunia
    0.26
     använda
    0.26
     benar
    0.25
    POSITIVE LOGITS
    ER
    0.36
    ರ್‌
    0.31
    у
    0.31
    ّد
    0.28
    ر
    0.28
    UR
    0.27
     ၀
    0.27
    يند
    0.27
    јединачна
    0.27
    ERTS
    0.27
    Activations Density 0.008%

    No Known Activations