© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 212787
    Prev
    Next
    INDEX
    Explanations

    the

    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_50_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
     prefecture
    0.43
    arde
    0.37
     agate
    0.36
    assuming
    0.35
     turmeric
    0.35
    picture
    0.34
    GO
    0.34
    府
    0.34
    urchase
    0.34
    GENERAL
    0.34
    POSITIVE LOGITS
    inals
    0.48
    нца
    0.41
    стки
    0.41
    ngl
    0.41
     букмекердик
    0.40
    ļ
    0.40
    스티
    0.40
     Elli
    0.39
     سوز
    0.39
    变革
    0.39
    Activations Density 0.001%

    No Known Activations