© 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. 9293
    Prev
    Next
    INDEX
    Explanations

    code snippets, particularly in PHP, HTML, Javascript, and XML.

    oai_token-act-pair · gemini-2.0-flash

    Web Development source code

    np_max-act-logits · gemini-2.0-flash
    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
    <bos>
    -0.68
     pon
    -0.50
    مراجع
    -0.46
    적인
    -0.44
     Bowl
    -0.43
     Bow
    -0.43
     الرياضيه
    -0.43
    ald
    -0.43
    APORE
    -0.41
     wy
    -0.41
    POSITIVE LOGITS
     Theſe
    0.61
     Shakspeare
    0.55
     propOrder
    0.54
     myſelf
    0.54
    ScopeManager
    0.52
     preſent
    0.50
     ſeveral
    0.50
     Shaksp
    0.49
     becauſe
    0.48
     Armageddon
    0.48
    Activations Density 1.740%

    No Known Activations