© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4594
    Prev
    Next
    INDEX
    Explanations

    technical language used to describe medical procedures

    oai_token-act-pair · gemini-2.0-flash

    ultrasound

    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
    ChildScrollView
    -0.57
    XmlSchema
    -0.48
    뉜
    -0.46
     GoogleFonts
    -0.46
    Fns
    -0.46
     کش
    -0.45
    tisseur
    -0.45
    悴
    -0.45
    ViewImports
    -0.44
     Barrington
    -0.44
    POSITIVE LOGITS
     son
    1.15
     Son
    0.98
    Son
    0.94
    son
    0.86
     SON
    0.78
    SON
    0.76
     sons
    0.72
    sono
    0.71
     grandson
    0.69
     lenker
    0.68
    Activations Density 1.569%

    No Known Activations