© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 47138
    Prev
    Next
    INDEX
    Explanations

    sugarcane

    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_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Supp
    0.93
    ри
    0.91
    י
    0.90
    Sup
    0.88
    ي
    0.87
     sup
    0.86
    sup
    0.84
    supp
    0.83
     suppress
    0.81
     Supp
    0.80
    POSITIVE LOGITS
    u
    0.70
     Tigers
    0.65
     Fukushima
    0.63
    нг
    0.63
     Inquisition
    0.62
    ியின்
    0.61
    рт
    0.60
     Aztecs
    0.60
    URLException
    0.60
    йня
    0.59
    Activations Density 0.001%

    No Known Activations