© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13946
    Prev
    Next
    INDEX
    Explanations

    references to drinking, beverages, food and tradition, specifically within the context of meals and celebrations.

    oai_token-act-pair · gemini-2.0-flash

    restaurants and bars

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     nakalista
    -0.48
    gin
    -0.47
     SPIR
    -0.47
     spirit
    -0.47
    jelen
    -0.47
     Walkover
    -0.46
    kent
    -0.45
    bi
    -0.45
    SPIR
    -0.45
     spirits
    -0.44
    POSITIVE LOGITS
     cigarettes
    0.62
    SceneManagement
    0.60
    mybatisplus
    0.60
     cigarette
    0.60
    PreExecute
    0.60
     Cakes
    0.59
     barista
    0.59
    LookAnd
    0.58
    InjectAttribute
    0.57
     moustache
    0.57
    Activations Density 2.786%

    No Known Activations