© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8707
    Prev
    Next
    INDEX
    Explanations

    title for plots

    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_13_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
     costruito
    0.58
     vendido
    0.57
     ingest
    0.53
     cuc
    0.52
    вати
    0.52
     scelto
    0.52
     товары
    0.51
    พวกเขา
    0.51
    ...";
    0.50
     sitio
    0.49
    POSITIVE LOGITS
    sled
    0.60
    ar
    0.52
    oral
    0.51
     enthusiastic
    0.51
    sh
    0.51
    il
    0.50
    reality
    0.50
    mushroom
    0.50
    忍不住
    0.50
    human
    0.49
    Activations Density 0.016%

    No Known Activations