© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 30803
    Prev
    Next
    INDEX
    Explanations

    router configuration and administration

    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_31_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
    盃
    0.39
     Absence
    0.39
    XH
    0.39
     resourceful
    0.38
     বুক
    0.38
    absence
    0.36
     SOLUTIONS
    0.36
    тение
    0.36
     ভু
    0.35
    푥
    0.35
    POSITIVE LOGITS
     remains
    0.38
    vy
    0.37
     Manual
    0.36
     colours
    0.36
     flavour
    0.36
     فنا
    0.36
    人群
    0.36
     copper
    0.36
    dome
    0.35
     سنی
    0.35
    Activations Density 0.074%

    No Known Activations