© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 127599
    Prev
    Next
    INDEX
    Explanations

    Pauli, Hermann, Bertrand

    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_37_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
    Herm
    0.51
     Herm
    0.43
     herm
    0.42
    矇
    0.42
     годом
    0.41
     দারি
    0.40
     monsieur
    0.39
    Pear
    0.39
    LAMP
    0.38
    巖
    0.38
    POSITIVE LOGITS
     maybe
    0.45
    去
    0.39
    ++)
    0.35
    maybe
    0.35
    ération
    0.35
     Serena
    0.35
     سك
    0.35
     去
    0.34
     perhaps
    0.33
     Maybe
    0.33
    Activations Density 0.000%

    No Known Activations