© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13955
    Prev
    Next
    INDEX
    Explanations

    quick, short, or expedited

    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
    હ
    0.38
    瓦
    0.38
    https
    0.36
    שית
    0.36
    ク
    0.36
    hatikan
    0.36
    ال
    0.35
    オレンジ
    0.35
    \}$
    0.35
    Σ
    0.34
    POSITIVE LOGITS
     quick
    0.44
    quick
    0.43
     rapide
    0.41
     rushed
    0.41
     quickest
    0.41
     rápido
    0.40
     chóng
    0.40
     быстро
    0.39
    fowl
    0.38
     швид
    0.38
    Activations Density 0.080%

    No Known Activations