© 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. 13507
    Prev
    Next
    INDEX
    Explanations

    HTML div and button tags and related elements

    oai_token-act-pair · gemini-2.0-flash

    HTML elements and attributes

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

    div

    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
     tranſ
    -0.63
     quæ
    -0.57
     ſeveral
    -0.56
    pacs
    -0.56
     ſtand
    -0.56
     miſ
    -0.56
     pleaſure
    -0.56
     greateſt
    -0.55
     juſ
    -0.55
     ſame
    -0.55
    POSITIVE LOGITS
    TintMode
    0.71
    :✨
    0.62
     ErrIntOverflow
    0.59
    cyclopedia
    0.56
    WriteBarrier
    0.56
    actylus
    0.55
     ModelExpression
    0.53
    quirrel
    0.50
     class
    0.50
    UnusedPrivate
    0.49
    Activations Density 0.598%

    No Known Activations