© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 135283
    Prev
    Next
    INDEX
    Explanations

    Sheeran

    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_1_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
     is
    1.34
     américain
    1.22
    的
    1.09
    ки
    1.09
    на
    1.01
     électronique
    1.01
     isotope
    0.99
    ал
    0.98
     américaine
    0.96
     langues
    0.96
    POSITIVE LOGITS
    In
    1.16
    If
    1.16
    It
    1.15
    Ī
    1.12
    Ĭ
    1.05
    Let
    0.96
    </td>
    0.96
    UT
    0.91
    To
    0.91
    ON
    0.88
    Activations Density 0.000%

    No Known Activations