© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24040
    Prev
    Next
    INDEX
    Explanations

    sticky substance properties

    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_10_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
    ge
    0.68
    ada
    0.58
    ers
    0.58
    ene
    0.57
    ina
    0.56
    eme
    0.56
    ه
    0.55
    irk
    0.54
    ellers
    0.54
    iv
    0.53
    POSITIVE LOGITS
     sticky
    0.71
    EX
    0.66
    は
    0.63
     viscous
    0.59
    sticky
    0.59
     Sticky
    0.59
    ي
    0.58
    ای
    0.55
     v
    0.55
    是
    0.55
    Activations Density 0.023%

    No Known Activations