© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 101508
    Prev
    Next
    INDEX
    Explanations

    language components

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
     Executes
    0.45
    贅
    0.36
     Execute
    0.35
    uf
    0.35
     An
    0.35
    iona
    0.34
     Tres
    0.34
     Complete
    0.33
    ionali
    0.32
    Архи
    0.32
    POSITIVE LOGITS
    ของการ
    0.42
    avadoc
    0.38
    ക്കായി
    0.38
    shoz
    0.36
    带来的
    0.36
    บ้าง
    0.35
    𝑟
    0.35
    の部分
    0.35
    των
    0.35
     glyphicon
    0.35
    Activations Density 0.009%

    No Known Activations