© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84557
    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_0_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
    t
    0.55
    medicine
    0.54
     time
    0.52
    ll
    0.49
    開き
    0.49
    mail
    0.48
     sauce
    0.48
    i
    0.48
     sucr
    0.48
     \
    0.47
    POSITIVE LOGITS
    рити
    0.53
    最重要的
    0.48
    fäh
    0.42
    ೃತ
    0.42
    בול
    0.42
     industrialized
    0.41
    Methylsulfanyl
    0.41
    ]).
    0.40
    Benzyloxy
    0.40
     Etappe
    0.39
    Activations Density 0.000%

    No Known Activations