© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 40708
    Prev
    Next
    INDEX
    Explanations

    EMIEW

    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_3_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
    _
    0.98
    ää
    0.71
    '
    0.65
    ani
    0.55
     medicines
    0.54
     hacía
    0.53
     reassurance
    0.53
    posals
    0.53
    ě
    0.53
    _',
    0.52
    POSITIVE LOGITS
    يد
    0.93
    ال
    0.84
    ر
    0.79
    ف
    0.79
    人
    0.74
    ي
    0.73
    satz
    0.73
    스
    0.73
    ق
    0.72
    ى
    0.71
    Activations Density 0.006%

    No Known Activations