© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 149638
    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_60_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
     (\
    0.38
    ~(\
    0.38
    ...\
    0.36
     προς
    0.36
    to
    0.35
     stren
    0.34
    და
    0.34
    \_
    0.33
    verifica
    0.33
     himself
    0.33
    POSITIVE LOGITS
    m
    0.54
    sr
    0.49
    ierre
    0.49
    illot
    0.48
    erais
    0.47
    inology
    0.47
    illah
    0.47
    aik
    0.46
    urier
    0.46
    erees
    0.46
    Activations Density 0.000%

    No Known Activations