© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 137695
    Prev
    Next
    INDEX
    Explanations

    AI assistant introduction

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Brown
    0.52
    茱
    0.47
    Columbia
    0.46
     brown
    0.42
     Brown
    0.41
    Bard
    0.39
     ቲ
    0.39
     Ph
    0.38
    Bharat
    0.38
     Columbia
    0.38
    POSITIVE LOGITS
     FMC
    0.40
    공
    0.38
     দেখে
    0.38
    ウト
    0.37
    ོང་
    0.36
     ني
    0.35
     நி
    0.34
    这么
    0.34
     हाता
    0.34
     Nesta
    0.34
    Activations Density 0.023%

    No Known Activations