© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 137082
    Prev
    Next
    INDEX
    Explanations

    at a level

    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_46_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
    惜
    0.38
    င်း
    0.38
    enzi
    0.37
     crowned
    0.36
    offline
    0.35
    pug
    0.34
    ByDefault
    0.34
    ษัท
    0.33
     Ministry
    0.33
     प्रॉपर्टी
    0.33
    POSITIVE LOGITS
     雪
    0.39
    وریت
    0.38
    वर
    0.37
    obacter
    0.36
    基本
    0.36
     есть
    0.35
     اتش
    0.35
    基本的
    0.35
    Tem
    0.34
    mus
    0.34
    Activations Density 0.003%

    No Known Activations