© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 247302
    Prev
    Next
    INDEX
    Explanations

    Enumerable methods like flat, reverse, and new

    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_40_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     размер
    0.42
     จัด
    0.41
     <--
    0.40
    ตัน
    0.39
     расход
    0.39
     Remove
    0.39
    Lessons
    0.38
    .--
    0.38
     Fujita
    0.38
     सॉ
    0.38
    POSITIVE LOGITS
    욤
    0.36
     புகை
    0.36
    sean
    0.36
     mydict
    0.35
    ongen
    0.35
    ainkan
    0.35
    ormais
    0.34
     flat
    0.34
    main
    0.33
     embargo
    0.33
    Activations Density 0.000%

    No Known Activations