© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 205557
    Prev
    Next
    INDEX
    Explanations

    also some

    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_20_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
     little
    0.29
    brug
    0.27
     pouco
    0.27
    嘞
    0.27
    വില്‍
    0.27
    ियल
    0.26
     other
    0.26
     knocks
    0.26
    thor
    0.26
    <0xC2>
    0.26
    POSITIVE LOGITS
    EOS
    0.28
    Blooming
    0.27
    פל
    0.27
    규모
    0.27
    acti
    0.27
    جة
    0.26
     направления
    0.26
     находиться
    0.26
    Jung
    0.26
    ITC
    0.26
    Activations Density 0.000%

    No Known Activations