© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 129718
    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_50_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     DAN
    0.43
    dan
    0.42
    DAN
    0.40
     žal
    0.40
     dan
    0.39
    άν
    0.38
    ｪ
    0.38
    fö
    0.38
    nX
    0.38
    NI
    0.38
    POSITIVE LOGITS
     столи
    0.37
    ⭒
    0.36
    羢
    0.36
    टीसी
    0.36
    ığımız
    0.35
     quint
    0.35
     essentiel
    0.35
     Nullam
    0.35
     vigorous
    0.35
    vindos
    0.34
    Activations Density 0.000%

    No Known Activations