© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 62745
    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
    Negative Logits
    to
    1.57
    an
    1.43
    ان
    1.41
     to
    1.39
    9
    1.34
    ak
    1.32
    are
    1.32
    un
    1.29
    ing
    1.27
    .
    1.27
    POSITIVE LOGITS
    I
    1.05
    ซ์
    0.87
    ཀ
    0.85
     einzigen
    0.84
    ഗ
    0.82
    C
    0.82
    らしく
    0.80
    kannya
    0.79
    كة
    0.78
     없이
    0.77
    Activations Density 0.000%

    No Known Activations