© 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-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13353
    Prev
    Next
    INDEX
    Explanations

    descriptions of inventions, especially their names and inventors

    oai_token-act-pair · gemini-2.0-flash

    origin

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    numerusform
    -0.57
     partielle
    -0.55
    ptonshire
    -0.54
    цездатний
    -0.53
    HasAnnotation
    -0.53
     eletrônico
    -0.51
     onOptions
    -0.50
     indépendante
    -0.50
     intellectuelle
    -0.50
    PhysRevLett
    -0.50
    POSITIVE LOGITS
     origin
    1.89
     origins
    1.88
     originated
    1.71
     Origin
    1.70
    Origin
    1.66
    origin
    1.64
     Origins
    1.64
    origins
    1.52
    ORIGIN
    1.50
     origen
    1.49
    Activations Density 2.742%

    No Known Activations