© 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-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14895
    Prev
    Next
    INDEX
    Explanations

    technical terminology for describing anatomy and medical imaging measurements

    oai_token-act-pair · gemini-2.0-flash

    Scientific measurements and locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -0.87
    المناصب
    -0.85
     '\\;'
    -0.82
     الرياضيه
    -0.81
     contextLoads
    -0.77
     doubtnut
    -0.76
    utilisons
    -0.75
    mybatisplus
    -0.74
     Վերցված
    -0.74
     helft
    -0.73
    POSITIVE LOGITS
     ro
    0.56
     superior
    0.52
     super
    0.47
     rost
    0.46
    ante
    0.45
     med
    0.45
    super
    0.45
     vent
    0.44
    D
    0.44
     D
    0.43
    Activations Density 2.378%

    No Known Activations