© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 129
    Prev
    Next
    INDEX
    Explanations

    names of months, dates, times, URLs, and other date/time related tokens.

    oai_token-act-pair · gemini-2.0-flash

    dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     pinulongan
    -0.77
    :✨
    -0.75
     Biôgrafia
    -0.71
     Roskov
    -0.63
     برانيه
    -0.63
    awaiter
    -0.63
    stateMutability
    -0.63
     CreateTagHelper
    -0.62
     disambiguazione
    -0.61
    انيف
    -0.59
    POSITIVE LOGITS
    <bos>
    0.54
    breadcrumbs
    0.44
    tiz
    0.43
    Statics
    0.42
    HttpFoundation
    0.40
    TabStop
    0.39
    SupportActionBar
    0.39
    IBOutlet
    0.38
    usiai
    0.38
    ঝ
    0.38
    Activations Density 28.814%

    No Known Activations