© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 121415
    Prev
    Next
    INDEX
    Explanations

    bundled with

    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_3_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
    a
    1.25
    1
    0.95
    ir
    0.91
    n
    0.89
    e
    0.85
    o
    0.79
    u
    0.78
    s
    0.77
    an
    0.75
    った
    0.71
    POSITIVE LOGITS
    مة
    0.68
    م
    0.68
    isti
    0.61
     الع
    0.60
     organizaciones
    0.58
     olvidar
    0.58
     is
    0.57
     harán
    0.57
    entities
    0.57
    بان
    0.56
    Activations Density 0.000%

    No Known Activations