© 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. 121476
    Prev
    Next
    INDEX
    Explanations

    on and off states

    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
    Negative Logits
    d
    0.88
    мара
    0.80
    $
    0.78
     Фурга
    0.76
    お客
    0.74
    CriteriaUtils
    0.72
    InterfaceLine
    0.70
    𝟘
    0.70
     CtApp
    0.70
     lặng
    0.69
    POSITIVE LOGITS
     to
    1.03
     t
    0.88
     l
    0.82
     o
    0.79
     U
    0.75
    ्य
    0.72
     robot
    0.72
     life
    0.72
     oil
    0.72
     trout
    0.71
    Activations Density 0.002%

    No Known Activations