© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 200058
    Prev
    Next
    INDEX
    Explanations

    competitive performance and advantage

    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_37_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
     teammates
    0.89
     teammate
    0.80
    team
    0.79
     team
    0.78
    チーム
    0.78
    팀
    0.76
     팀
    0.72
    队友
    0.71
     टीम
    0.70
    团队
    0.65
    POSITIVE LOGITS
    소서
    0.39
    職員
    0.38
    forum
    0.38
    Return
    0.38
     工作
    0.38
     форум
    0.37
     controlar
    0.37
     profissionais
    0.36
    コントロール
    0.36
     работой
    0.36
    Activations Density 0.022%

    No Known Activations