© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 235673
    Prev
    Next
    INDEX
    Explanations

    cannot provide legal or official documentation

    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_25_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
    emore
    0.45
    తులను
    0.38
     sowohl
    0.37
     any
    0.37
     Copeland
    0.37
     Faj
    0.37
     nbfs
    0.37
     느낌
    0.36
    ѐ
    0.36
     Alderman
    0.36
    POSITIVE LOGITS
    लो
    0.39
     системой
    0.37
     কমিটি
    0.37
    竟然
    0.36
    condition
    0.35
     መን
    0.35
    ᴹ
    0.35
     internationaux
    0.34
    ^{*}\
    0.34
    buscador
    0.34
    Activations Density 0.009%

    No Known Activations