© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41199
    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_22_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
    瑁
    0.58
    ഹം
    0.46
    争取
    0.46
    حة
    0.46
    िपल
    0.45
    ငံ
    0.44
    予以
    0.43
     הרו
    0.43
     kom
    0.43
    ޔ
    0.43
    POSITIVE LOGITS
     alarming
    0.45
    ฟ้า
    0.45
     ótima
    0.44
    高
    0.42
     alarms
    0.41
    𝐨
    0.41
     outage
    0.41
     تمہ
    0.41
     sugary
    0.41
    am
    0.40
    Activations Density 0.000%

    No Known Activations