© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 156549
    Prev
    Next
    INDEX
    Explanations

    press

    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_50_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
     pudding
    0.62
     Pudding
    0.52
     pudd
    0.48
     пу
    0.40
     density
    0.39
    푸
    0.38
     pud
    0.38
     D
    0.38
    лум
    0.38
    िद
    0.37
    POSITIVE LOGITS
     press
    1.20
     Press
    1.11
    press
    1.09
    Press
    1.06
     PRESS
    0.95
     प्रेस
    0.89
     presse
    0.89
    PRESS
    0.86
     Presse
    0.84
     пресс
    0.83
    Activations Density 0.060%

    No Known Activations