© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44490
    Prev
    Next
    INDEX
    Explanations

    也 connected to outcomes

    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_13_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
    鎳
    0.57
     russe
    0.50
     tablero
    0.49
     dùng
    0.49
     chassis
    0.49
     fournisseur
    0.49
     burrito
    0.49
     suisse
    0.49
     cocinar
    0.49
    REGIUNE
    0.48
    POSITIVE LOGITS
    n
    0.79
    н
    0.70
    of
    0.64
    it
    0.64
    h
    0.64
    at
    0.63
    r
    0.61
    os
    0.60
    (
    0.60
    ت
    0.59
    Activations Density 0.002%

    No Known Activations