© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 33411
    Prev
    Next
    INDEX
    Explanations

    fermented, health, aged, black, seniors

    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_31_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
    TRANSPORT
    0.42
     автоном
    0.41
     Pra
    0.40
    罌
    0.39
    kreuz
    0.39
    Cours
    0.38
    креп
    0.37
    标
    0.37
    Pra
    0.37
    ডিয়াম
    0.37
    POSITIVE LOGITS
     건강
    0.54
     health
    0.53
     Health
    0.48
     gesund
    0.46
     farm
    0.46
    健康
    0.46
     健康
    0.44
     आरोग्य
    0.44
     healthful
    0.44
     sveik
    0.43
    Activations Density 0.028%

    No Known Activations