© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 58830
    Prev
    Next
    INDEX
    Explanations

    tkinter widgets and properties

    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_11_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
     ]
    0.47
    ").
    0.45
     {
    0.44
    ="
    0.43
     dù
    0.42
     daha
    0.41
    <0x80>
    0.41
     sö
    0.41
     />
    0.41
     ence
    0.40
    POSITIVE LOGITS
     ಅವರಿಗೆ
    0.46
    名の
    0.43
     rousing
    0.42
    浮
    0.40
    ラッピング
    0.38
    を有する
    0.38
    殺
    0.38
    ционной
    0.37
     bicyclists
    0.37
    攪
    0.37
    Activations Density 0.020%

    No Known Activations