© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 135226
    Prev
    Next
    INDEX
    Explanations

    transformed into

    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_1_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
    ار
    1.27
    _
    1.00
    im
    0.94
    am
    0.94
    em
    0.94
    um
    0.91
     transcoding
    0.90
    sede
    0.89
    lle
    0.87
    Με
    0.87
    POSITIVE LOGITS
    o
    1.04
    ни
    1.00
    ↵↵
    0.96
     Accesat
    0.95
    я
    0.94
    ة
    0.94
     was
    0.92
     will
    0.92
     to
    0.92
     acest
    0.92
    Activations Density 0.001%

    No Known Activations