© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 29779
    Prev
    Next
    INDEX
    Explanations

    ug followed by na or uda

    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_7_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
    á
    1.57
    í
    1.27
    \
    1.27
    4
    1.23
    ä
    1.16
    ين
    1.13
    ž
    1.06
    ö
    1.05
    3
    1.04
    ice
    1.02
    POSITIVE LOGITS
    杠
    0.98
    誑
    0.87
     三
    0.82
     asympt
    0.80
    CUSSION
    0.79
     embers
    0.78
     הנו
    0.76
    ানন্দ
    0.75
    こだわ
    0.75
    とっても
    0.74
    Activations Density 0.000%

    No Known Activations