© 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. 212117
    Prev
    Next
    INDEX
    Explanations

    button properties and actions

    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
    ige
    0.40
    city
    0.40
     \&
    0.39
    agor
    0.38
    era
    0.38
     オフィス
    0.37
    𝗷
    0.37
    igor
    0.37
     વોર્
    0.36
    iger
    0.36
    POSITIVE LOGITS
    บวน
    0.35
    Ν
    0.33
     त्यासाठी
    0.33
    ΡΑ
    0.33
     Kindly
    0.32
    ває
    0.32
     mouthful
    0.32
    บท
    0.32
     courting
    0.32
     workmanship
    0.32
    Activations Density 0.000%

    No Known Activations