© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 60914
    Prev
    Next
    INDEX
    Explanations

    quarks and QCD

    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
     quais
    0.57
    ):
    0.55
     corrobor
    0.54
     (“
    0.52
    quando
    0.52
     spontaneity
    0.52
     opulent
    0.51
    .):
    0.50
    unghi
    0.50
     spontaneously
    0.50
    POSITIVE LOGITS
    した
    0.52
    ＿
    0.52
     значення
    0.51
    ItemBackground
    0.51
     విలువ
    0.50
     veilig
    0.50
     безопасность
    0.49
    ಬ
    0.49
     ख्
    0.48
    +](=
    0.48
    Activations Density 0.003%

    No Known Activations