© 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. 162581
    Prev
    Next
    INDEX
    Explanations

    pearson

    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
    t
    1.45
    ين
    1.13
    і
    1.12
    ية
    1.11
    ında
    1.08
    h
    1.07
    soever
    1.03
    IN
    1.00
    ൈ
    0.99
     인해
    0.96
    POSITIVE LOGITS
    is
    1.34
     for
    1.27
    ک
    1.11
    ي
    1.08
    י
    0.96
    ut
    0.96
    ب
    0.95
     י
    0.91
    자리
    0.91
    其他
    0.90
    Activations Density 0.000%

    No Known Activations