© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35081
    Prev
    Next
    INDEX
    Explanations

    Nationalist Ireland party

    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_11_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
     підтрим
    0.59
     домаћин
    0.56
     നെറ്റ്‌വർ
    0.54
     فوجی
    0.54
    也會
    0.54
     позволит
    0.54
     powin
    0.53
     поддержки
    0.53
    衊
    0.53
     будут
    0.52
    POSITIVE LOGITS
    De
    0.55
    ',
    0.53
     De
    0.53
    Higher
    0.52
    3
    0.51
    AST
    0.51
    Six
    0.50
     de
    0.50
    '
    0.50
     principle
    0.49
    Activations Density 0.006%

    No Known Activations