© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14636
    Prev
    Next
    INDEX
    Explanations

    section

    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
    悉
    0.40
     RESOL
    0.38
    GetAll
    0.37
     Daerah
    0.35
    Lieutenant
    0.35
    面積
    0.34
    庥
    0.34
    faculty
    0.33
    ச
    0.33
    ونز
    0.33
    POSITIVE LOGITS
     section
    1.21
     sections
    1.00
    section
    0.98
     sección
    0.92
     seção
    0.86
     sezione
    0.83
     chapter
    0.80
     bölüm
    0.80
     Abschnitt
    0.79
    sections
    0.78
    Activations Density 0.166%

    No Known Activations