© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 140449
    Prev
    Next
    INDEX
    Explanations

    code, programming, data

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    としての
    0.37
     mediante
    0.35
     بواسطة
    0.35
    ことができる
    0.34
     हेतु
    0.34
     unmistak
    0.34
    ということです
    0.33
    🤽
    0.33
    ด้อ
    0.33
     atthe
    0.33
    POSITIVE LOGITS
    Iniciar
    0.39
    Ordenar
    0.35
    urezza
    0.35
     Entwick
    0.35
     literatura
    0.34
    鐏
    0.34
     پلان
    0.33
     revista
    0.33
     inspired
    0.33
     braid
    0.33
    Activations Density 0.104%

    No Known Activations