© 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. 15321
    Prev
    Next
    INDEX
    Explanations

    up followed by ials

    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
    th
    0.57
     nghe
    0.57
    were
    0.55
    ளாவ
    0.54
     jovens
    0.52
     nervously
    0.52
    ۔
    0.52
     মুহাম্ম
    0.51
     듣
    0.50
     interwoven
    0.49
    POSITIVE LOGITS
     Mother
    0.55
     माता
    0.53
     தாய
    0.52
     mother
    0.52
     catchment
    0.50
     Konink
    0.50
     মাতা
    0.49
     Ос
    0.48
     protrusions
    0.48
     KAP
    0.48
    Activations Density 0.003%

    No Known Activations