© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13318
    Prev
    Next
    INDEX
    Explanations

    mostly junk characters in this corpus. It also finds bracketed sections and the word "view."

    oai_token-act-pair · gemini-2.0-flash

    HTML code, URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    клопе
    -0.61
    InputBorder
    -0.60
    InSection
    -0.51
    reszcie
    -0.49
    OpenHelper
    -0.48
    makeConstraints
    -0.48
    umą
    -0.48
    WithMany
    -0.47
    uxxxx
    -0.47
    DataGridView
    -0.47
    POSITIVE LOGITS
     怎样
    0.63
     Administrativna
    0.61
     énergé
    0.59
     EconPapers
    0.58
     ligiloj
    0.57
    Lähteet
    0.56
    مراجع
    0.56
    ']))
    0.55
    bart
    0.54
    قر
    0.54
    Activations Density 1.640%

    No Known Activations