© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 140862
    Prev
    Next
    INDEX
    Explanations

    avoiding unnecessary

    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_12_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
    مت
    0.25
    खिक
    0.22
     subjecting
    0.22
    خر
    0.22
     mittens
    0.22
     unemployed
    0.22
    u
    0.21
    تد
    0.21
    Ін
    0.21
    n
    0.21
    POSITIVE LOGITS
     sAlarm
    0.24
    TOUR
    0.24
    shopify
    0.24
     дополни
    0.23
    ড়ায়
    0.23
     بیشتر
    0.22
    roph
    0.22
     larva
    0.22
     дополнительные
    0.21
    お客
    0.21
    Activations Density 0.001%

    No Known Activations