© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 175249
    Prev
    Next
    INDEX
    Explanations

    place names

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     dav
    0.41
     пане
    0.38
    Ctx
    0.38
    ctx
    0.37
     Два
    0.37
     G
    0.37
     ctx
    0.37
     deductive
    0.36
     πυ
    0.36
    。<
    0.36
    POSITIVE LOGITS
     Roque
    0.46
     sequester
    0.42
    বিমান
    0.42
     Bunker
    0.41
    aptop
    0.41
    FERRED
    0.41
    Mont
    0.41
    몬
    0.39
     Simon
    0.39
    লায়
    0.39
    Activations Density 0.000%

    No Known Activations