© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2512
    Prev
    Next
    INDEX
    Explanations

    words related to car technology and features, especially lighting and display

    oai_token-act-pair · gemini-2.0-flash

    chrome

    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
     gæ
    -0.47
    uanya
    -0.47
     list
    -0.45
    AUT
    -0.43
    ieso
    -0.43
    耕
    -0.42
    pie
    -0.40
     input
    -0.40
     data
    -0.40
     same
    -0.40
    POSITIVE LOGITS
     resourceCulture
    0.84
    expandindo
    0.77
     snippetHide
    0.76
    Халык
    0.75
     Савезне
    0.74
    Obrázky
    0.73
     transfieras
    0.71
    WithIOException
    0.69
    Personendaten
    0.69
    السكان
    0.69
    Activations Density 0.755%

    No Known Activations