© 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. 12339
    Prev
    Next
    INDEX
    Explanations

    language used in legal contracts and agreements

    oai_token-act-pair · gemini-2.0-flash

    legal/policy agreements

    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
     sogni
    -0.69
     InputDecoration
    -0.69
    MemoryWarning
    -0.67
     flyknit
    -0.59
     magnétique
    -0.58
    ImageContext
    -0.58
    msgTypes
    -0.57
     vierge
    -0.57
     palk
    -0.57
    IGraphics
    -0.54
    POSITIVE LOGITS
     kasarigan
    0.59
    Begriffsklä
    0.50
    llus
    0.49
    brigens
    0.48
    ęty
    0.48
    archiviato
    0.47
     الحره
    0.46
    BeginContext
    0.46
    TabLayout
    0.46
    GEBURTSDATUM
    0.45
    Activations Density 2.036%

    No Known Activations