© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 64849
    Prev
    Next
    INDEX
    Explanations

    numbers and foreign words

    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_51_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
     У
    1.38
     Ud
    1.31
    乌
    1.30
     U
    1.30
    宇
    1.27
     ud
    1.23
    Ud
    1.23
     Udd
    1.22
     ウ
    1.20
     อุ
    1.20
    POSITIVE LOGITS
     сте
    0.40
     نمبر
    0.40
    㱛
    0.39
     ste
    0.38
    ৈ
    0.38
     SSm
    0.36
     सश
    0.36
     SS
    0.36
    仯
    0.35
     ಪ್ರಾ
    0.35
    Activations Density 0.044%

    No Known Activations