© 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
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10096
    Prev
    Next
    INDEX
    Explanations

    NASA technical paper numbers (TP) and letter/proposal requirements

    oai_token-act-pair · gemini-2.0-flash

    documents with numbers

    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
    StructEnd
    -0.59
     CreateTagHelper
    -0.56
    TableAdapter
    -0.53
    gafas
    -0.52
     متعلقه
    -0.52
     ویکی‌پدی
    -0.52
    ApiModel
    -0.52
     betweenstory
    -0.52
    XtraReports
    -0.51
     دیکھیے
    -0.51
    POSITIVE LOGITS
     ModelExpression
    0.56
    уда
    0.56
     ens
    0.50
    tagHelperRunner
    0.49
     siv
    0.48
    busch
    0.47
     sides
    0.47
     fl
    0.43
     ende
    0.42
    [,]
    0.42
    Activations Density 2.571%

    No Known Activations