© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 208899
    Prev
    Next
    INDEX
    Explanations

    insurance terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    ssc
    0.38
    ogin
    0.36
     hydride
    0.36
     ஒது
    0.35
    mounted
    0.35
     telur
    0.35
    ancang
    0.34
    ể
    0.34
     الشي
    0.34
    promo
    0.34
    POSITIVE LOGITS
     Group
    0.73
     Term
    0.68
     group
    0.67
    Term
    0.66
    Group
    0.64
     term
    0.62
     GROUP
    0.62
    group
    0.61
     grupp
    0.60
     grup
    0.56
    Activations Density 0.001%

    No Known Activations