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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 33502
    Prev
    Next
    INDEX
    Explanations

    political transition and reconciliation

    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_31_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
     guerra
    0.33
     guerre
    0.30
    /*'
    0.30
    /*',
    0.28
    ListenAndServe
    0.28
     प्रतीक्षा
    0.27
     warfare
    0.27
    야
    0.27
     combats
    0.27
    戦
    0.26
    POSITIVE LOGITS
    sped
    0.35
     reconstruction
    0.34
     reconstructed
    0.31
     Reconstruction
    0.31
     Roberto
    0.30
     रीजन
    0.30
    工夫
    0.30
    修复
    0.29
     reconstructing
    0.29
    重建
    0.29
    Activations Density 0.006%

    No Known Activations