© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 64024
    Prev
    Next
    INDEX
    Explanations

    Changes

    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_59_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
    Makes
    0.81
     Makes
    0.78
     makes
    0.72
    makes
    0.72
    make
    0.60
     make
    0.60
    Make
    0.59
     делает
    0.57
     M
    0.55
     maakt
    0.52
    POSITIVE LOGITS
     over
    0.72
     Made
    0.66
     made
    0.63
    made
    0.61
    Made
    0.59
    Over
    0.53
     über
    0.50
    over
    0.50
     Over
    0.50
    過
    0.50
    Activations Density 0.006%

    No Known Activations