© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 19583
    Prev
    Next
    INDEX
    Explanations

    become something

    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_15_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
     \|
    0.32
     करून
    0.30
    Ҡ
    0.30
    aceous
    0.30
    энне
    0.29
    edLeft
    0.29
     ኤ
    0.29
     sowohl
    0.28
    astien
    0.28
    الصفحه
    0.28
    POSITIVE LOGITS
     laborales
    0.27
    piar
    0.26
    を生
    0.26
    нія
    0.26
    鉄道
    0.25
    ва
    0.25
    萌
    0.25
    Labor
    0.25
    פס
    0.25
     ווא
    0.25
    Activations Density 0.020%

    No Known Activations