© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136255
    Prev
    Next
    INDEX
    Explanations

    ASEAN countries and members

    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_12_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
    ’
    0.53
    aus
    0.52
    ormal
    0.51
     disposto
    0.51
    ário
    0.49
             
    0.49
     Lucas
    0.47
    ausch
    0.47
     procurar
    0.47
    a
    0.47
    POSITIVE LOGITS
    php
    0.61
    tson
    0.59
     sulphuric
    0.57
    지컬
    0.57
    ৫৮
    0.56
    鿉
    0.56
    𝐠
    0.55
     AppBsky
    0.55
    𝐥
    0.54
     forth
    0.54
    Activations Density 0.001%

    No Known Activations