© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 226623
    Prev
    Next
    INDEX
    Explanations

    "ezayak" and Arabic interrogatives

    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_6_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
    و
    0.41
    gium
    0.40
    ges
    0.40
    在
    0.40
    annya
    0.39
    gruppe
    0.38
     في
    0.38
    alten
    0.38
    ពី
    0.38
    idium
    0.38
    POSITIVE LOGITS
    s
    0.57
    ü
    0.55
    ’
    0.51
     to
    0.49
     campsites
    0.48
    <0x0D>
    0.47
     hospitals
    0.47
     atk
    0.47
    sü
    0.47
     airplanes
    0.47
    Activations Density 0.000%

    No Known Activations