© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48094
    Prev
    Next
    INDEX
    Explanations

    registration and applications

    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_31_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
     Bernhard
    0.42
     artistique
    0.41
     রিসার্চ
    0.39
     umjet
    0.38
     Prozesse
    0.38
    OrEqualTo
    0.37
     FormData
    0.36
     Discounts
    0.36
    ড়াই
    0.36
    🥉
    0.36
    POSITIVE LOGITS
    書類
    0.40
    лично
    0.39
    metaTag
    0.39
     документи
    0.37
    rica
    0.37
    れて
    0.37
    حه
    0.36
     अस्त
    0.36
    laptop
    0.36
    categoria
    0.36
    Activations Density 0.003%

    No Known Activations