© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 17221
    Prev
    Next
    INDEX
    Explanations

    concave and convex functions

    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_15_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
     occupation
    0.51
    দীর
    0.50
     растений
    0.49
     supplementing
    0.48
    ленного
    0.48
    occupation
    0.48
     alder
    0.48
    㻴
    0.47
    کاری
    0.47
    सेल
    0.47
    POSITIVE LOGITS
    ϲ
    0.64
     rifer
    0.53
    ㏄
    0.49
     بہت
    0.49
     ERISA
    0.48
     Dota
    0.48
     இருக்கு
    0.48
    Andrews
    0.47
     Dublin
    0.47
     nagyon
    0.47
    Activations Density 0.003%

    No Known Activations