© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2086
    Prev
    Next
    INDEX
    Explanations

    technological devices and associated functionalities, with a potential emphasis on privacy concerns.

    oai_token-act-pair · gemini-2.0-flash

    webcams and cameras

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     visitors
    -0.46
     instant
    -0.44
     hồng
    -0.43
    instant
    -0.43
    glMatrixMode
    -0.42
     bezoekers
    -0.41
    fficio
    -0.41
    AutoScaleMode
    -0.41
     khiển
    -0.40
    bufio
    -0.40
    POSITIVE LOGITS
     مرئيه
    0.82
    TagMode
    0.80
    
    0.77
     StatelessWidget
    0.71
    ValueStyle
    0.71
    Tikang
    0.70
    AntiForgeryToken
    0.66
    ########.
    0.66
    Datuak
    0.66
    setVerticalGroup
    0.66
    Activations Density 29.421%

    No Known Activations