© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44339
    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_13_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
    a
    0.78
    an
    0.77
    b
    0.63
    m
    0.63
    g
    0.59
    re
    0.58
    ان
    0.58
    T
    0.58
    y
    0.56
    z
    0.52
    POSITIVE LOGITS
     rū
    0.59
     leptonic
    0.54
     drunkenness
    0.53
     یہودیوں
    0.51
     без
    0.51
     Jerez
    0.51
     αποτε
    0.50
     сто
    0.50
     १६
    0.50
     receitas
    0.50
    Activations Density 0.000%

    No Known Activations