© 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. 234335
    Prev
    Next
    INDEX
    Explanations

    include

    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
    Edge
    0.43
    edge
    0.42
    র্ষ
    0.41
     Edge
    0.39
    шы
    0.38
    䒩
    0.38
     మి
    0.38
    oddsidemargin
    0.37
     edge
    0.36
     folhas
    0.36
    POSITIVE LOGITS
    framework
    0.41
    Framework
    0.41
     framework
    0.40
    框架
    0.39
     πό
    0.38
    ंटा
    0.38
     فض
    0.38
     TA
    0.37
    LinkForm
    0.37
    框
    0.37
    Activations Density 0.001%

    No Known Activations