© 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. 57895
    Prev
    Next
    INDEX
    Explanations

    surgical procedures and surgeons

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ك
    1.41
    ться
    1.38
    å
    1.33
    ного
    1.30
    פ
    1.29
    ಿದರೆ
    1.26
    ρα
    1.24
    ंग
    1.16
    с
    1.16
    σ
    1.16
    POSITIVE LOGITS
    i
    1.80
    ות
    1.43
    <0x0D>
    1.37
     by
    1.30
    0
    1.26
    리
    1.21
     camped
    1.05
     ০
    1.04
    -
    1.02
     chino
    1.00
    Activations Density 0.002%

    No Known Activations