© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 101278
    Prev
    Next
    INDEX
    Explanations

    just for fun

    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_14_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
    🧬
    0.17
     mediante
    0.16
     মাটি
    0.16
     પોતાના
    0.15
     _)
    0.15
    硅
    0.15
     гипсо
    0.15
    WallArray
    0.14
     مصدر
    0.14
     congé
    0.14
    POSITIVE LOGITS
    рт
    0.16
    з
    0.16
    incing
    0.16
    зация
    0.16
    ローブ
    0.15
    ไลน์
    0.15
    aining
    0.14
     collapse
    0.14
     года
    0.14
    スタート
    0.14
    Activations Density 0.011%

    No Known Activations