© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 206222
    Prev
    Next
    INDEX
    Explanations

    protein complexes

    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_19_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
    窍
    0.45
     கர்ப்ப
    0.41
    雑
    0.39
     Filtering
    0.39
    髒
    0.39
     Ingredients
    0.38
     Jop
    0.38
     ንጥረ
    0.38
     घरा
    0.38
    滤
    0.38
    POSITIVE LOGITS
    с
    0.48
    de
    0.46
     escaped
    0.45
    ret
    0.45
    ihu
    0.42
    zte
    0.41
    ⃣
    0.41
    lich
    0.41
    cannot
    0.41
     escapes
    0.40
    Activations Density 0.001%

    No Known Activations