© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18460
    Prev
    Next
    INDEX
    Explanations

    Rust traits

    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
     légèrement
    0.58
    ę
    0.57
     Egipto
    0.56
     Gitar
    0.55
    ječ
    0.55
     Gesù
    0.55
    ಾಯಿತು
    0.54
     Özel
    0.54
     Kā
    0.53
    ja
    0.53
    POSITIVE LOGITS
     marketplace
    0.50
     jubilee
    0.49
    บู
    0.48
    จับ
    0.48
     anthropology
    0.46
    ผ
    0.45
    ֗
    0.43
     banquet
    0.43
    的服务
    0.43
     serial
    0.43
    Activations Density 0.001%

    No Known Activations