© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 247367
    Prev
    Next
    INDEX
    Explanations

    Emperor of the French

    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_40_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
    лур
    0.46
     attentively
    0.44
    ič
    0.41
     Cian
    0.40
     ஏ
    0.39
    vi
    0.38
    newdata
    0.37
    lian
    0.36
    یاط
    0.36
     Rotten
    0.35
    POSITIVE LOGITS
     ምን
    0.42
     confinement
    0.40
     Infinity
    0.37
     stof
    0.37
     চাঁদ
    0.37
    zp
    0.36
     concert
    0.35
     )(
    0.35
     stirrer
    0.35
     ት
    0.34
    Activations Density 0.001%

    No Known Activations