© 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. 113546
    Prev
    Next
    INDEX
    Explanations

    story, locations, or revival

    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
    د
    1.09
    д
    0.97
    ник
    0.91
    го
    0.90
     lié
    0.89
    ിയും
    0.88
     accueill
    0.87
     entreg
    0.86
     alcanz
    0.86
     atteint
    0.85
    POSITIVE LOGITS
    at
    1.25
    an
    1.25
    on
    1.20
    r
    1.15
    et
    1.13
    a
    1.09
    er
    0.98
    s
    0.95
    en
    0.93
    us
    0.93
    Activations Density 0.000%

    No Known Activations