© 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. 15055
    Prev
    Next
    INDEX
    Explanations

    code snippets followed by a semicolon or parentheses

    oai_token-act-pair · gemini-2.0-flash

    days of the week

    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
     Sunday
    -0.93
    Sunday
    -0.89
     Saturday
    -0.85
     sunday
    -0.82
     SUNDAY
    -0.82
     seventh
    -0.81
    Saturday
    -0.80
     eighth
    -0.77
     søndag
    -0.76
     saturday
    -0.75
    POSITIVE LOGITS
     Wednesday
    0.60
    Wednesday
    0.54
     WEDNESDAY
    0.53
     mercredi
    0.50
     Wednesdays
    0.47
    AddressBook
    0.46
     printemps
    0.45
    sandwich
    0.45
    ednesday
    0.44
    UrlResolution
    0.44
    Activations Density 0.351%

    No Known Activations