© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 58015
    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_2_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
     نہيں
    1.13
     غير
    0.98
     براي
    0.95
    س
    0.93
     aumentada
    0.93
     مؤرشف
    0.91
     morrer
    0.91
    ди
    0.91
    д
    0.88
    𝕥
    0.88
    POSITIVE LOGITS
    ل
    1.50
    '
    1.36
    ↵
    1.32
    an
    1.02
    l
    1.00
    k
    0.97
    le
    0.95
    er
    0.94
     can
    0.94
    $
    0.94
    Activations Density 0.000%

    No Known Activations