© 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. 13576
    Prev
    Next
    INDEX
    Explanations

    the word "class", often designating a category or type

    oai_token-act-pair · gemini-2.0-flash

    class

    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
    deepcopy
    -0.57
    Formik
    -0.54
     Downvote
    -0.52
     Bearer
    -0.51
    ederos
    -0.50
     ")");
    -0.50
     WebElement
    -0.49
     Pikachu
    -0.49
     Baptism
    -0.48
     ivelany
    -0.48
    POSITIVE LOGITS
     surla
    0.67
    Sucesor
    0.58
    Alguien
    0.52
    PYX
    0.51
    sunter
    0.50
    IsPostBack
    0.49
     vPvB
    0.49
     IConfiguration
    0.47
    føring
    0.47
     CreateTagHelper
    0.46
    Activations Density 4.702%

    No Known Activations