© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 237610
    Prev
    Next
    INDEX
    Explanations

    html/css/javascript code

    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_32_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
    teryx
    0.41
     reporting
    0.39
    二
    0.38
     ट्रिपल
    0.36
     తగ్
    0.36
     النو
    0.35
     Pipeline
    0.35
    ராட்ச
    0.34
     scorecard
    0.34
     succeeds
    0.33
    POSITIVE LOGITS
    шот
    0.40
    erno
    0.39
    Ꮙ
    0.39
     Wien
    0.38
    copies
    0.38
     assurent
    0.38
    NOTE
    0.38
    튀
    0.38
     softmax
    0.37
     asigur
    0.37
    Activations Density 0.010%

    No Known Activations