© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7933
    Prev
    Next
    INDEX
    Explanations

    sorority, fraternity, house, robotics, James

    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_40_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
    冥
    0.37
     BOOST
    0.35
    ंग्रे
    0.35
    Suppress
    0.34
    ULA
    0.34
    鄱
    0.34
     ದೇಹ
    0.34
    ｺ
    0.33
    অন
    0.33
    Eight
    0.33
    POSITIVE LOGITS
     philanthropy
    0.47
    рил
    0.45
     IFC
    0.45
    颧
    0.40
    ipun
    0.39
    ophilus
    0.39
     sing
    0.38
     philanthrop
    0.38
    ichten
    0.38
     мате
    0.38
    Activations Density 0.009%

    No Known Activations