© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 202216
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_6_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
    اب
    0.75
     spectator
    0.75
    يرات
    0.75
    週間
    0.74
    ätzen
    0.73
    ’
    0.73
    钀
    0.73
    적
    0.73
     کننده
    0.72
    ATION
    0.71
    POSITIVE LOGITS
     In
    1.10
    <h2>
    1.03
    os
    1.01
    ۔
    1.00
    ib
    0.98
    ل
    0.93
    ි
    0.93
    arı
    0.93
    af
    0.91
    an
    0.90
    Activations Density 0.000%

    No Known Activations