© 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. 57557
    Prev
    Next
    INDEX
    Explanations

    backslash escapes

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     I
    2.02
     L
    1.59
     U
    1.50
    en
    1.41
     K
    1.41
    n
    1.41
     M
    1.34
     T
    1.30
     G
    1.30
    i
    1.29
    POSITIVE LOGITS
    د
    1.20
    2
    1.20
    quela
    1.14
    ح
    1.06
    大
    0.97
    ished
    0.96
    ного
    0.95
    ssel
    0.95
    نيه
    0.94
    ้ย
    0.93
    Activations Density 0.001%

    No Known Activations