© 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. 197887
    Prev
    Next
    INDEX
    Explanations

    endings of sentences and phrases

    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
    u
    0.64
    CI
    0.56
    ART
    0.53
    i
    0.52
    AD
    0.50
    _
    0.49
    도
    0.49
     zwią
    0.48
     in
    0.47
     meshes
    0.47
    POSITIVE LOGITS
    می
    0.58
    보니
    0.58
    보
    0.58
    مد
    0.57
    ز
    0.56
    becue
    0.54
    ли
    0.54
    有所
    0.53
    ए
    0.53
    jší
    0.52
    Activations Density 0.000%

    No Known Activations