© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4216
    Prev
    Next
    INDEX
    Explanations

    dishes and their ingredients from restaurant menus or reviews.

    oai_token-act-pair · gemini-2.0-flash

    technical terms or programming-related identifiers

    np_token-act-pair-logits · gpt-4o-mini

    food reviews

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     kalite
    -0.40
    harusnya
    -0.40
    Pode
    -0.39
    irish
    -0.38
    icioso
    -0.38
    tető
    -0.38
     entlang
    -0.36
    κή
    -0.36
     pouvons
    -0.36
     vorbei
    -0.35
    POSITIVE LOGITS
     propOrder
    0.78
    errHandler
    0.77
    UserScript
    0.74
    Искәрмәләр
    0.71
    ########.
    0.71
    WebElementEntity
    0.68
    Datuak
    0.68
     архивлан
    0.68
    ⓧ
    0.67
    ValueGeneration
    0.66
    Activations Density 3.955%

    No Known Activations