© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 76852
    Prev
    Next
    INDEX
    Explanations

    German

    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_53_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
     r
    0.46
     ρ
    0.41
     Ver
    0.40
     Poverty
    0.39
    句
    0.39
     ر
    0.38
     Tariff
    0.38
     صاف
    0.36
    のと
    0.36
     Hare
    0.36
    POSITIVE LOGITS
    ming
    0.40
     grantee
    0.39
    mero
    0.39
    unsch
    0.39
     sistemat
    0.39
    ]^{
    0.38
    西哥
    0.38
     mering
    0.38
     명이
    0.38
    RequestListener
    0.37
    Activations Density 0.017%

    No Known Activations