© 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
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 6960
    Prev
    Next
    INDEX
    Explanations

    unspecified diagnoses and body parts

    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
     presentations
    0.37
     বজায়
    0.36
    ޘ
    0.36
    ViewModel
    0.35
     type
    0.35
    EventHandler
    0.35
    预览
    0.34
    ृत
    0.34
     ระยะ
    0.34
    FAs
    0.34
    POSITIVE LOGITS
    絕
    0.45
    mlin
    0.42
    med
    0.42
    生き
    0.42
    abelian
    0.40
    embal
    0.39
    绝
    0.38
     gepubliceerd
    0.38
    itee
    0.38
    globin
    0.37
    Activations Density 0.008%

    No Known Activations