© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 102991
    Prev
    Next
    INDEX
    Explanations

    AA, Order, Venus, Nerve

    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_14_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
     abstinence
    0.54
     EXAMINATION
    0.54
     rearing
    0.53
     whipping
    0.52
     examination
    0.47
     benefiting
    0.47
    ப்புற
    0.46
    竜
    0.46
     emulation
    0.46
    hatan
    0.46
    POSITIVE LOGITS
     vidrio
    0.54
     silice
    0.53
    colo
    0.51
    ib
    0.51
     tissus
    0.51
    insuku
    0.51
     хоть
    0.50
    嬲
    0.50
    ónico
    0.50
     olla
    0.49
    Activations Density 0.000%

    No Known Activations