© 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. 211927
    Prev
    Next
    INDEX
    Explanations

    row inserting, expansion, background color

    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
    韬
    0.23
    btn
    0.22
    resolve
    0.22
    梯度
    0.22
     Grammy
    0.21
    intl
    0.21
     పెట్టు
    0.21
     stint
    0.21
    ترى
    0.21
    quatre
    0.21
    POSITIVE LOGITS
    Owing
    0.26
     Owing
    0.25
    oting
    0.24
    ي
    0.23
    openqa
    0.23
     classifying
    0.23
    মুখি
    0.23
     ovarian
    0.23
     derece
    0.23
     पोर्न
    0.23
    Activations Density 0.002%

    No Known Activations