© 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. 106983
    Prev
    Next
    INDEX
    Explanations

    Spanish, Korean, or other language beginnings

    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
     of
    1.27
    ate
    1.10
    <0x80>
    0.96
    
    0.96
    0.94
    LED
    0.93
    >
    0.84
    er
    0.83
    u
    0.83
    る
    0.83
    POSITIVE LOGITS
    س
    1.45
    ¹.
    1.13
    １
    1.04
    های
    1.02
    1
    1.01
    ک
    1.01
    リ
    1.00
    жи
    1.00
    리
    1.00
    ुलम
    0.98
    Activations Density 0.000%

    No Known Activations