© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 161211
    Prev
    Next
    INDEX
    Explanations

    centering content

    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_31_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
    iftung
    0.39
    ^{*}(\
    0.36
    皇帝
    0.36
     поез
    0.36
    ቨ
    0.36
     превы
    0.35
     crainte
    0.35
    HING
    0.35
     сма
    0.35
     महाराजा
    0.35
    POSITIVE LOGITS
     commentaries
    0.38
     version
    0.36
    abilidades
    0.36
    ებები
    0.36
    逍
    0.36
     territorio
    0.36
     partager
    0.35
     পক্ষের
    0.35
     teams
    0.35
     signatory
    0.35
    Activations Density 0.001%

    No Known Activations