© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 115301
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_27_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
     Norway
    0.39
     Sumer
    0.38
     William
    0.37
     Innovation
    0.35
     Norwegian
    0.34
    4
    0.34
     Summer
    0.33
    蒲
    0.33
     Little
    0.33
     bravery
    0.33
    POSITIVE LOGITS
    ENCIAS
    0.42
     Фонбет
    0.41
    issie
    0.38
    rencies
    0.38
    ifie
    0.38
     वोटर
    0.37
    läuft
    0.37
     }}(\
    0.37
    尷
    0.37
    ennzeichnet
    0.37
    Activations Density 0.000%

    No Known Activations