© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36372
    Prev
    Next
    INDEX
    Explanations

    Christianity, sovereignty, Word of God

    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
    Not in Any Lists

    No Comments

    Negative Logits
    t
    0.50
     viewing
    0.48
     departure
    0.45
     настолько
    0.45
     arrival
    0.44
     bier
    0.43
    zicht
    0.43
      
    0.43
     batch
    0.43
     stylesheet
    0.42
    POSITIVE LOGITS
     میں
    0.61
    いた
    0.57
    (/[
    0.56
    
    0.56
    ີ
    0.55
    ೋಗ್ಯ
    0.55
     도움이
    0.55
     медици
    0.54
     Agua
    0.54
    খে
    0.53
    Activations Density 0.005%

    No Known Activations