© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12471
    Prev
    Next
    INDEX
    Explanations

    words with common political, coding, or cat-based animal themes.

    oai_token-act-pair · gemini-2.0-flash

    cat domestic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    Cat
    -0.85
     Cat
    -0.84
     cat
    -0.78
    cat
    -0.75
     domestic
    -0.75
     domésticos
    -0.74
    domestic
    -0.71
     Domestic
    -0.66
    Domestic
    -0.64
     domés
    -0.63
    POSITIVE LOGITS
    GEBURTSDATUM
    0.84
    تقاوى
    0.68
     &___
    0.67
     utafitiHapana
    0.66
     חיצוניים
    0.64
     resourceCulture
    0.63
    aarrggbb
    0.62
     ModelExpression
    0.62
    WebElementEntity
    0.59
    ########.
    0.59
    Activations Density 13.819%

    No Known Activations