© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 212024
    Prev
    Next
    INDEX
    Explanations

    numbered lists starting with "1."

    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_20_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
     sugar
    0.34
     dairy
    0.33
    िशन
    0.32
     sexual
    0.32
     poultry
    0.30
    جم
    0.30
    ój
    0.29
    ग्रा
    0.29
    药
    0.29
     cane
    0.29
    POSITIVE LOGITS
     montagna
    0.35
     passaggio
    0.34
     mehrerer
    0.32
     Measure
    0.32
    sembled
    0.31
     weiterer
    0.30
     Від
    0.30
     Durchmesser
    0.30
     Foli
    0.29
     FURTHER
    0.29
    Activations Density 0.002%

    No Known Activations