© 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. 212716
    Prev
    Next
    INDEX
    Explanations

    pressure, strain, emotional

    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
    ిన
    0.44
     为
    0.44
    3
    0.44
     oras
    0.43
     แปล
    0.42
    迟
    0.42
     pg
    0.42
    ing
    0.41
     vx
    0.41
    ل
    0.41
    POSITIVE LOGITS
    ESTIC
    0.48
    źć
    0.47
     पूर्व
    0.45
     scrotum
    0.45
    naeus
    0.45
     tath
    0.43
    tabPadding
    0.43
    띄
    0.43
    octopus
    0.43
     mieć
    0.43
    Activations Density 0.000%

    No Known Activations