© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7090
    Prev
    Next
    INDEX
    Explanations

    the words "Pad" or "Cad/Ca" followed by additional characters

    oai_token-act-pair · gemini-2.0-flash

    cad/pad

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ficulties
    -0.49
    역
    -0.45
     zewnętrzne
    -0.43
    trane
    -0.42
     Gefahr
    -0.40
     ple
    -0.39
     sterili
    -0.39
    urgis
    -0.39
    дов
    -0.39
    bé
    -0.39
    POSITIVE LOGITS
    AndEndTag
    0.73
    CompleteListener
    0.70
    msgTypes
    0.65
    LookAnd
    0.63
     autorytatywna
    0.63
    PropertyChanging
    0.62
    tagHelperRunner
    0.62
     étro
    0.61
     تضيفلها
    0.60
    Искәрмәләр
    0.60
    Activations Density 0.847%

    No Known Activations