© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 245175
    Prev
    Next
    INDEX
    Explanations

    http server boilerplate

    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_40_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
     Walk
    0.40
    ALIAS
    0.39
     WALK
    0.39
     caminho
    0.37
     notepad
    0.37
    劒
    0.36
     مات
    0.35
    enaar
    0.35
    alias
    0.34
    建設
    0.34
    POSITIVE LOGITS
     አገልግሎ
    0.40
     दक्षिणी
    0.39
     unprotected
    0.38
     curt
    0.38
     consign
    0.37
     अल्ट्रा
    0.37
    セイ
    0.37
    स्वा
    0.37
    ऑ
    0.37
     eiusmod
    0.37
    Activations Density 0.001%

    No Known Activations