© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 67601
    Prev
    Next
    INDEX
    Explanations

    parental leave

    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_41_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
     کرتی
    0.40
    質な
    0.40
    かく
    0.37
    ௭
    0.37
     ऑल
    0.36
    ponen
    0.36
    वर्ती
    0.35
    扑
    0.35
     vacío
    0.35
    KeyboardView
    0.35
    POSITIVE LOGITS
     leave
    1.41
     Leave
    1.39
    leave
    1.27
    Leave
    1.24
     leaves
    1.08
    Leaves
    1.00
     Leaves
    0.98
    leaves
    0.88
     leaving
    0.78
     оставить
    0.71
    Activations Density 0.000%

    No Known Activations