© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15082
    Prev
    Next
    INDEX
    Explanations

    numbers and currency amounts

    oai_token-act-pair · gemini-2.0-flash

    numbers and units

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     Efq
    -0.77
     Reſ
    -0.61
    AccessorTable
    -0.59
     nearly
    -0.59
     Theſe
    -0.58
    ceria
    -0.57
    LookAnd
    -0.57
     UIFont
    -0.56
    +:+
    -0.56
     leaſt
    -0.56
    POSITIVE LOGITS
    something
    0.64
    Something
    0.54
    AddTagHelper
    0.52
    来人
    0.52
     Something
    0.52
     something
    0.52
     internes
    0.51
     Exactos
    0.51
    scryfall
    0.50
    xtext
    0.50
    Activations Density 1.193%

    No Known Activations