© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 209735
    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_5_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
    。
    1.28
    that
    1.24
     that
    1.09
    。)
    1.03
    </h2>
    1.02
    holder
    0.98
     Religion
    0.95
    </span>
    0.94
     to
    0.94
    。“
    0.93
    POSITIVE LOGITS
    is
    1.22
    erà
    1.17
    ক
    1.16
     dès
    1.14
    ер
    1.13
    ığı
    1.12
     nerveux
    1.08
    at
    1.07
     prévue
    1.07
    бро
    1.06
    Activations Density 0.000%

    No Known Activations