© 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. 140201
    Prev
    Next
    INDEX
    Explanations

    random

    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
    EOUS
    0.45
    下旬
    0.44
    虻
    0.43
     Samantha
    0.41
     उत्तरी
    0.41
     människ
    0.41
    ᕇ
    0.41
     civilizations
    0.40
     Eski
    0.40
     ملتی
    0.40
    POSITIVE LOGITS
     SPR
    0.41
     fpr
    0.41
           
    0.38
     하나
    0.37
     έγ
    0.37
    =
    0.36
     spr
    0.35
    PR
    0.35
     dtype
    0.35
     element
    0.34
    Activations Density 0.002%

    No Known Activations