© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3191
    Prev
    Next
    INDEX
    Explanations

    the word "page" in the context of URLs and code

    oai_token-act-pair · gemini-2.0-flash

    structured page elements or formats

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

    Page

    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
    ніципа
    -0.71
     <>",
    -0.70
     Winaray
    -0.69
     Signalez
    -0.69
     Infórmanos
    -0.68
     cherchés
    -0.68
    FailureListener
    -0.66
    cookieParser
    -0.64
    </tfoot>
    -0.64
     ویکی‌پدیای
    -0.63
    POSITIVE LOGITS
    boc
    0.47
    WebControls
    0.47
     vpon
    0.45
    text
    0.45
    дя
    0.43
    ีย
    0.41
    Neat
    0.41
    licata
    0.40
    稽
    0.40
    順
    0.40
    Activations Density 3.777%

    No Known Activations