© 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. 215219
    Prev
    Next
    INDEX
    Explanations

    officials and authorities report

    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
     وین
    0.38
    ந்துக
    0.35
    质疑
    0.35
    லோச
    0.35
    筝
    0.34
    岁的
    0.33
    Compounds
    0.33
    indsight
    0.33
     sintet
    0.32
     जडेजा
    0.32
    POSITIVE LOGITS
     dishwasher
    0.38
     preserve
    0.38
     गए
    0.37
    printer
    0.37
    ಬೇ
    0.35
     Character
    0.34
     Exceptional
    0.34
    preserve
    0.34
    到
    0.34
     ہیں۔
    0.34
    Activations Density 0.000%

    No Known Activations