© 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. 36937
    Prev
    Next
    INDEX
    Explanations

    say verb endings

    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
    Not in Any Lists

    No Comments

    Negative Logits
    으로
    0.91
     것으로
    0.75
     으로
    0.67
    로
    0.67
     olarak
    0.63
    で
    0.59
    として
    0.55
    事で
    0.52
    자로
    0.51
     म्हणून
    0.49
    POSITIVE LOGITS
     suv
    0.45
     লী
    0.42
    pecia
    0.41
     onda
    0.40
     Onda
    0.39
    ডির
    0.38
    pen
    0.37
    ਦਾ
    0.37
    нед
    0.37
    論
    0.37
    Activations Density 0.001%

    No Known Activations