© 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. 205657
    Prev
    Next
    INDEX
    Explanations

    chemicals and manufacturing

    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
    ianSpace
    0.36
    唝
    0.36
    પ્
    0.35
    abbam
    0.35
    ंचित
    0.35
     মিলিয়ন
    0.35
    啭
    0.35
    ကယ်
    0.34
     löyty
    0.34
     বেতন
    0.34
    POSITIVE LOGITS
    String
    0.44
     String
    0.38
    化
    0.37
    STR
    0.36
    <tr>
    0.35
    ing
    0.35
     S
    0.35
     di
    0.35
    udge
    0.34
     Wax
    0.34
    Activations Density 0.028%

    No Known Activations