© 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
    2. Gemma-3-27B-IT
    3. 14-GEMMASCOPE-2-TRANSCODER-262K
    4. 99792
    Prev
    Next
    INDEX
    Explanations

    CERN physics research

    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_14_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
     Lebensmittel
    0.55
    зо
    0.52
     Supportive
    0.51
     ді
    0.51
     শক্তিশালী
    0.51
     १०
    0.49
     оз
    0.49
     Р
    0.48
     움
    0.48
     продовжу
    0.48
    POSITIVE LOGITS
    Apache
    0.53
    "]
    0.52
     aeroplane
    0.51
    Donc
    0.51
    agricult
    0.51
    "],
    0.50
    Records
    0.50
    records
    0.50
    Fox
    0.50
    Jest
    0.50
    Activations Density 0.000%

    No Known Activations