© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7472
    Prev
    Next
    INDEX
    Explanations

    output:

    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_39_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
     अधिसू
    0.40
     یونیورسٹی
    0.39
     updater
    0.39
     イタリア
    0.38
     thoughtfully
    0.38
     தெரிவி
    0.38
    𒌓
    0.38
    PubKey
    0.38
    ॅम्प
    0.37
     কোটি
    0.37
    POSITIVE LOGITS
    output
    0.47
    Output
    0.41
     rink
    0.40
     java
    0.39
     output
    0.38
    Main
    0.38
    OUTPUT
    0.38
    楞
    0.37
    bug
    0.37
    java
    0.37
    Activations Density 0.054%

    No Known Activations