© 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. 1870
    Prev
    Next
    INDEX
    Explanations

    phrases indicating awareness of something, especially in a legal context.

    oai_token-act-pair · gemini-2.0-flash

    court rulings

    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
    Autoritní
    -0.89
    AsUp
    -0.88
    StoryboardSegue
    -0.84
    BindingResult
    -0.82
    esgue
    -0.81
     Мексичка
    -0.77
     CreateTagHelper
    -0.76
    StructEnd
    -0.76
    Tikang
    -0.75
    onedDateTime
    -0.75
    POSITIVE LOGITS
     _
    0.45
     peringatan
    0.45
     G
    0.44
     sexuales
    0.44
     corris
    0.43
    sh
    0.42
     gyerek
    0.42
     fisik
    0.41
    ローズ
    0.41
    IQR
    0.41
    Activations Density 0.883%

    No Known Activations