© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4212
    Prev
    Next
    INDEX
    Explanations

    strings and URI prefixes related to XML namespaces, web addresses and Android development

    oai_token-act-pair · gemini-2.0-flash

    http

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    ViewFeatures
    -0.73
     CreateTagHelper
    -0.66
     المعيارى
    -0.65
     intptr
    -0.62
    dientemente
    -0.60
    tagHelperRunner
    -0.60
    estars
    -0.60
     unconnected
    -0.59
    lious
    -0.59
     OFDb
    -0.59
    POSITIVE LOGITS
    <bos>
    1.86
    <h2>
    0.56
    .*")]
    0.53
     financières
    0.47
     régle
    0.47
    I
    0.47
    "
    0.46
     Meksiku
    0.46
    Step
    0.45
    “
    0.45
    Activations Density 2.408%

    No Known Activations