© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 55170
    Prev
    Next
    INDEX
    Explanations

    robotics code

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
     робо
    0.46
     mocked
    0.44
     роботи
    0.42
     robot
    0.42
     barn
    0.41
    _{[
    0.39
    elight
    0.39
     ridiculed
    0.39
    Grade
    0.39
     robotic
    0.39
    POSITIVE LOGITS
     Licensing
    0.43
     प्रद
    0.42
     അത
    0.40
    ค
    0.40
    `).
    0.39
     licensing
    0.38
    gems
    0.38
    ោធ
    0.38
    ہر
    0.37
     किं
    0.36
    Activations Density 0.000%

    No Known Activations