© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 195520
    Prev
    Next
    INDEX
    Explanations

    say "ies" ending

    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_46_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
    ('${
    0.41
    鉉
    0.38
    स्वर
    0.38
     olvidar
    0.38
    运作
    0.38
    avgsalary
    0.37
     trots
    0.37
    ("$
    0.36
     clásico
    0.36
     활용
    0.36
    POSITIVE LOGITS
     Meaning
    0.59
     meaning
    0.54
    meaning
    0.53
    Meaning
    0.48
     meanings
    0.46
    意味
    0.45
     หมาย
    0.42
    含义
    0.41
    หมาย
    0.40
     Advice
    0.40
    Activations Density 0.003%

    No Known Activations