© 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. 92063
    Prev
    Next
    INDEX
    Explanations

    company records

    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
    -
    1.00
    '
    0.94
    不
    0.73
    ed
    0.73
    小
    0.71
    টি
    0.71
     trabalh
    0.68
    全
    0.67
    O
    0.65
     recognize
    0.64
    POSITIVE LOGITS
    یت
    0.71
    یم
    0.67
    वता
    0.66
    लया
    0.65
    شی
    0.64
    بین
    0.63
    ⿹
    0.62
    ような
    0.62
    یش
    0.61
     प्रक्रिया
    0.61
    Activations Density 0.000%

    No Known Activations