© 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. 1740
    Prev
    Next
    INDEX
    Explanations

    words related to settings in applications or websites

    oai_token-act-pair · gemini-2.0-flash

    options, settings

    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
     
    -0.43
     iste
    -0.43
    dej
    -0.42
     Extremely
    -0.39
    Extremely
    -0.39
    iv
    -0.39
    V
    -0.38
     extremo
    -0.38
    0
    -0.38
    end
    -0.37
    POSITIVE LOGITS
     cherchés
    1.13
    NameInMap
    0.90
    Tembelea
    0.88
     ویکی‌پدیای
    0.87
     neceffary
    0.84
    OGND
    0.84
     externi
    0.84
     كومونز
    0.84
     quæ
    0.78
    awaiter
    0.78
    Activations Density 8.056%

    No Known Activations