© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 181236
    Prev
    Next
    INDEX
    Explanations

    ed

    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_24_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
     ellos
    0.46
    ુભ
    0.46
    ರಿ
    0.44
     trochu
    0.44
     Vib
    0.44
    感が
    0.43
    揺
    0.43
     cinco
    0.43
     anglais
    0.43
    旅館
    0.43
    POSITIVE LOGITS
    的情况下
    0.41
     添加
    0.39
     实现
    0.39
    添加到
    0.37
     혹은
    0.37
     买
    0.37
     Add
    0.36
    私募基金管理人
    0.36
    Основные
    0.35
    添加
    0.35
    Activations Density 0.001%

    No Known Activations