© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41216
    Prev
    Next
    INDEX
    Explanations

    is not

    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_22_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
    トム
    0.24
     รู้
    0.24
    રિક
    0.24
    蚋
    0.24
     மிரு
    0.24
     Seville
    0.23
    yard
    0.23
     Beetle
    0.23
     மன்னி
    0.23
     lawns
    0.23
    POSITIVE LOGITS
    Gameplay
    0.26
     중
    0.25
     chuyến
    0.25
    онів
    0.23
    응
    0.23
     vecchia
    0.23
    hôte
    0.23
     삼
    0.23
    朢
    0.23
     gameplay
    0.22
    Activations Density 0.000%

    No Known Activations