© 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. 30879
    Prev
    Next
    INDEX
    Explanations

    Munich

    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
    动
    1.56
     động
    1.48
    動
    1.45
    动的
    1.41
     動
    1.09
    동
    1.05
     dinam
    0.96
     динами
    0.96
     dynamic
    0.93
    Dynamic
    0.91
    POSITIVE LOGITS
    รส
    0.39
     pdelay
    0.38
     laut
    0.37
    pasar
    0.36
    elez
    0.36
    럽
    0.35
    ⑰
    0.35
    オート
    0.35
    педії
    0.35
     আর
    0.34
    Activations Density 0.001%

    No Known Activations