© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5364
    Prev
    Next
    INDEX
    Explanations

    calle, molinos, explicó, cabello, apresúrate, locales, ejemplo, palabras

    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_39_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
     پیش
    0.48
     پیشن
    0.47
     ایک
    0.45
     mū
    0.45
    ၡ
    0.45
     Vetter
    0.44
     পাঠ
    0.44
    かしい
    0.43
    เหมือน
    0.43
     Walpole
    0.43
    POSITIVE LOGITS
    amento
    0.68
    izado
    0.64
    í
    0.63
    adores
    0.62
    amentos
    0.62
    ador
    0.61
    ía
    0.60
    izador
    0.59
    ante
    0.59
    illo
    0.58
    Activations Density 0.162%

    No Known Activations