© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3945
    Prev
    Next
    INDEX
    Explanations

    seemingly random snippets of HTML and Javascript code

    oai_token-act-pair · gemini-2.0-flash

    Non-English words

    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
    zub
    -0.54
     légende
    -0.52
     الحره
    -0.52
    zám
    -0.50
    jmniej
    -0.49
    ima
    -0.48
    par
    -0.47
    Substring
    -0.46
     unavailable
    -0.46
     conse
    -0.46
    POSITIVE LOGITS
     unknownFields
    0.77
     مشين
    0.71
     autorytatywna
    0.69
     Paglinawan
    0.66
     Wikimedijinoj
    0.65
    MLLoader
    0.63
    AndEndTag
    0.61
     Chwiliwch
    0.61
     AspNetCore
    0.60
    webElement
    0.59
    Activations Density 0.291%

    No Known Activations