© 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
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 11199
    Prev
    Next
    INDEX
    Explanations

    uses of "this" and '.' in code, possibly related to object properties or methods, or the start of method definitions

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     parlant
    -0.60
     régle
    -0.58
    expandindo
    -0.57
    hoeddwyd
    -0.56
    rungsseite
    -0.55
    ActionMode
    -0.54
     publicitaires
    -0.54
    AddHtmlAttribute
    -0.52
     EdgeInsets
    -0.52
    webElementGuid
    -0.52
    POSITIVE LOGITS
     >=",
    0.62
    getchar
    0.61
    لينكات
    0.57
    #
    0.54
    存于互联网档案馆
    0.52
     كومونز
    0.50
     Référence
    0.49
    insular
    0.49
    GMENT
    0.49
    xygen
    0.48
    Activations Density 0.259%

    No Known Activations