© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7014
    Prev
    Next
    INDEX
    Explanations

    HTML and Javascript code, especially related to Bootstrap libraries and Angular routing

    oai_token-act-pair · gemini-2.0-flash

    website 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
     beginnetje
    -0.61
    IsMutable
    -0.60
     оригіналу
    -0.56
     AssemblyTitle
    -0.56
     ExecuteAsync
    -0.54
     blessés
    -0.54
    ennemi
    -0.54
    uxxxx
    -0.53
    AccessorTable
    -0.53
     Púb
    -0.53
    POSITIVE LOGITS
     Zeug
    0.53
    losis
    0.48
     Leone
    0.47
    hage
    0.47
    AddHtmlAttribute
    0.47
    клопе
    0.46
    Obrázky
    0.46
    道
    0.45
    bufio
    0.45
    <bos>
    0.44
    Activations Density 1.939%

    No Known Activations