© 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. 36898
    Prev
    Next
    INDEX
    Explanations

    brand names

    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
     P
    0.53
    P
    0.48
    Newton
    0.43
    Пе
    0.43
     Simpson
    0.41
    setP
    0.41
     पीस
    0.40
    森
    0.39
     Newton
    0.38
     مط
    0.38
    POSITIVE LOGITS
     lichen
    0.38
     underdog
    0.38
    jones
    0.38
     จังหวัด
    0.37
     간단
    0.36
     argument
    0.35
     Crocker
    0.35
     don
    0.35
    <0xA4>
    0.34
     κα
    0.34
    Activations Density 0.003%

    No Known Activations