© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 200062
    Prev
    Next
    INDEX
    Explanations

    precursor and impossible

    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_15_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
     Г
    0.61
     litt
    0.55
     引
    0.53
     เน
    0.53
     कानून
    0.50
     fach
    0.50
     Ψ
    0.49
     vírus
    0.49
     contém
    0.49
     senz
    0.49
    POSITIVE LOGITS
    0
    0.57
    you
    0.55
    Mon
    0.52
    Determine
    0.51
    First
    0.50
    Ban
    0.50
    trying
    0.50
    You
    0.49
    Remove
    0.49
    Dental
    0.48
    Activations Density 0.000%

    No Known Activations