© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 176588
    Prev
    Next
    INDEX
    Explanations

    indentured servitude, debt bondage, laborers

    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_20_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
     blackberries
    0.55
     Schwarz
    0.48
    <bos>
    0.48
     телефо
    0.46
    пки
    0.46
     telef
    0.46
     ინტერ
    0.46
     Monter
    0.45
    地说
    0.45
     varicose
    0.44
    POSITIVE LOGITS
    CCL
    0.41
    처리
    0.41
     erfolgreich
    0.40
     처리
    0.40
    Discrete
    0.39
     procesamiento
    0.39
    涣
    0.39
     את
    0.39
     ನೇ
    0.39
    Equivalent
    0.39
    Activations Density 0.001%

    No Known Activations