© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 254265
    Prev
    Next
    INDEX
    Explanations

    UK places

    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_56_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
    South
    0.45
     Zuid
    0.42
    南
    0.41
     South
    0.40
    KPI
    0.40
     south
    0.40
     جنوب
    0.39
     দক্ষি
    0.39
    SOUTH
    0.38
     दक्षिण
    0.38
    POSITIVE LOGITS
     bright
    0.64
    bright
    0.64
    Bright
    0.62
     Bright
    0.60
    亮
    0.52
     brightest
    0.51
     brighten
    0.49
    East
    0.49
     brighter
    0.47
     East
    0.46
    Activations Density 0.000%

    No Known Activations