© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 137231
    Prev
    Next
    INDEX
    Explanations

    setting values

    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_46_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
    tileSize
    0.41
     Salazar
    0.38
    Modulo
    0.37
    feet
    0.37
    揆
    0.37
     Skipper
    0.36
    proper
    0.36
     Modifier
    0.36
    
    0.36
    rier
    0.36
    POSITIVE LOGITS
    設定
    0.62
    を設定
    0.59
     설정
    0.58
    setting
    0.57
     Setting
    0.56
    の設定
    0.56
     ustaw
    0.55
     gesetzt
    0.55
     setting
    0.54
     設定
    0.54
    Activations Density 0.000%

    No Known Activations