© 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. 198102
    Prev
    Next
    INDEX
    Explanations

    numbers and anagrams

    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
    ส่
    0.50
    sz
    0.50
     چکی
    0.49
     akár
    0.48
     rése
    0.47
    ی
    0.46
     lintas
    0.46
     Dickinson
    0.45
    marshaller
    0.45
    sch
    0.44
    POSITIVE LOGITS
    拳
    0.51
    amantha
    0.50
    stüt
    0.50
    🫰
    0.47
     Hemos
    0.46
    istema
    0.46
    rizione
    0.45
     Tüm
    0.45
     Clusters
    0.45
     ساتھ
    0.44
    Activations Density 0.002%

    No Known Activations