© 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. 11479
    Prev
    Next
    INDEX
    Explanations

    descriptions of biological structures in the context of a wound experiment

    oai_token-act-pair · gemini-2.0-flash

    immune response and wounds

    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
     CreateTagHelper
    -1.05
    tagHelperRunner
    -0.91
    ंदीखरीदारी
    -0.88
    évaluateur
    -0.80
     MainAxisSize
    -0.75
     pleaſure
    -0.73
     @"/
    -0.71
     initComponents
    -0.69
     purpoſe
    -0.68
    Kariera
    -0.68
    POSITIVE LOGITS
     ro
    0.55
     pro
    0.54
     bas
    0.52
    bas
    0.49
     Pro
    0.49
     Mo
    0.48
     Con
    0.47
     t
    0.47
    ro
    0.46
     U
    0.46
    Activations Density 2.148%

    No Known Activations