© 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. 217362
    Prev
    Next
    INDEX
    Explanations

    triangle

    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
    Not in Any Lists

    No Comments

    Negative Logits
     constituted
    0.49
    പ്പാ
    0.41
     Antip
    0.40
    কমার
    0.38
     LIF
    0.37
    瑣
    0.36
    Bunch
    0.35
    KIS
    0.35
    ઉન
    0.35
    뷊
    0.35
    POSITIVE LOGITS
     Tri
    0.43
     삼각형
    0.41
     Dungeon
    0.41
     mg
    0.39
    mg
    0.39
    triangle
    0.39
    Tri
    0.39
     architecture
    0.39
     Mg
    0.38
     Triangle
    0.37
    Activations Density 0.001%

    No Known Activations