© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14928
    Prev
    Next
    INDEX
    Explanations

    code that parses and tests JavaScript

    oai_token-act-pair · gemini-2.0-flash

    Javascript 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_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    SystemColors
    -0.58
    AntiForgeryToken
    -0.57
    Seznam
    -0.56
    TagHelper
    -0.56
    XmlRootElement
    -0.54
     Caps
    -0.54
     Audiodateien
    -0.53
     ناد
    -0.53
     caps
    -0.52
    fare
    -0.52
    POSITIVE LOGITS
     Web
    0.63
    Web
    0.59
    ThroughAttribute
    0.53
     web
    0.52
     lèvres
    0.50
     SUDOC
    0.50
     otomatig
    0.50
    web
    0.49
     ansik
    0.48
     WEB
    0.47
    Activations Density 1.346%

    No Known Activations