© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 36877
    Prev
    Next
    INDEX
    Explanations

    always followed by verbs

    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_31_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
     Meditation
    0.30
     accl
    0.30
     meditations
    0.30
     shares
    0.30
     undergoing
    0.29
     Shares
    0.28
     Occasionally
    0.28
    Basil
    0.28
     bacter
    0.28
    ញ
    0.27
    POSITIVE LOGITS
     لمدة
    0.30
     პარ
    0.29
     dúvidas
    0.29
     pitan
    0.28
    复杂度
    0.28
    onomy
    0.28
    olinha
    0.28
    ulty
    0.27
     dúvida
    0.27
     પડશે
    0.27
    Activations Density 0.007%

    No Known Activations