© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 121919
    Prev
    Next
    INDEX
    Explanations

    programming interfaces and classes

    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
    Not in Any Lists

    No Comments

    Negative Logits
     फेव
    0.38
     শ্রেণি
    0.38
    MenuItemView
    0.36
     Kohler
    0.35
    
    0.34
     വിധ
    0.34
    コーヒー
    0.34
     Bronson
    0.34
    積極
    0.33
    瘍
    0.33
    POSITIVE LOGITS
     pq
    0.43
     expectations
    0.43
     estimates
    0.41
    rican
    0.41
     expectativas
    0.40
    xiety
    0.38
    જરા
    0.38
     directions
    0.38
     Unless
    0.38
    ക്കിയി
    0.37
    Activations Density 0.000%

    No Known Activations