© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2059
    Prev
    Next
    INDEX
    Explanations

    a wide variety of seemingly unrelated terms, including sports, clothing, mathematics, food, academia, geography, and even abstract concepts.

    oai_token-act-pair · gemini-2.0-flash

    function words

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     ujednoznacz
    -0.56
     pauvreté
    -0.52
     simplicité
    -0.52
     trö
    -0.50
     hendes
    -0.49
    出版年
    -0.49
    hamshire
    -0.49
     ruok
    -0.49
     maksi
    -0.49
    \{\\
    -0.47
    POSITIVE LOGITS
    Chham
    0.63
    ⓧ
    0.63
    oredCriteria
    0.61
     SqlDbType
    0.54
    MLLoader
    0.54
    dBm
    0.54
    JspWriter
    0.54
    ViewImports
    0.54
    ]++;
    0.53
    chọn
    0.53
    Activations Density 4.292%

    No Known Activations