© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 26674
    Prev
    Next
    INDEX
    Explanations

    numbers, programming, programming languages, code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
     "
    1.15
     “
    1.13
     ‘
    1.09
     `"
    1.02
     '
    1.00
     ”
    0.93
     ’
    0.92
     `'
    0.89
     「
    0.86
     ["
    0.84
    POSITIVE LOGITS
     संज्ञा
    0.42
    Verb
    0.40
     เส
    0.39
    ビジネス
    0.39
    PropertyName
    0.38
     الاسم
    0.38
     business
    0.37
    ார்க
    0.37
     ആരോ
    0.37
    Filename
    0.36
    Activations Density 0.164%

    No Known Activations