© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 154689
    Prev
    Next
    INDEX
    Explanations

    dimensions and measurements

    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_23_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
     מע
    0.43
    ដូច
    0.41
    identification
    0.41
     იქნება
    0.40
    Callable
    0.40
    砳
    0.40
    পর
    0.39
     valde
    0.39
    innovation
    0.38
     ایسا
    0.38
    POSITIVE LOGITS
     candied
    0.43
    лых
    0.41
    镇
    0.41
    kk
    0.40
    els
    0.40
    კ
    0.40
     Bars
    0.38
     t
    0.38
     ceremonial
    0.38
    sib
    0.38
    Activations Density 0.000%

    No Known Activations