© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 234306
    Prev
    Next
    INDEX
    Explanations

    money slang

    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
    QRST
    0.41
     আয়
    0.39
    ,\\
    0.38
    ',{
    0.38
    :\\
    0.37
    感染
    0.37
    重新
    0.36
    :"",
    0.36
    无需
    0.36
    倖
    0.36
    POSITIVE LOGITS
     whack
    0.71
     smack
    0.68
     dough
    0.64
     munch
    0.63
     kicks
    0.60
     kick
    0.57
     chow
    0.57
     gear
    0.56
     mugs
    0.54
     swag
    0.54
    Activations Density 0.001%

    No Known Activations