© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11736
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to time and duration, including dates, deliveries, and court sessions

    oai_token-act-pair · gemini-2.0-flash

    programming or technical terms related to software

    np_token-act-pair-logits · gpt-4o-mini

    Reported events

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     day
    -1.16
     seven
    -1.04
     everyday
    -1.00
     Day
    -0.97
     Monday
    -0.96
     daily
    -0.96
    day
    -0.94
    Day
    -0.93
     five
    -0.92
    Monday
    -0.91
    POSITIVE LOGITS
    RectangleBorder
    0.73
    FormTagHelper
    0.72
    DeleteBehavior
    0.69
    InvalidProtocol
    0.68
     ―――――
    0.68
     مرئيه
    0.68
     inflater
    0.66
    ConstraintMaker
    0.66
    TypedDataSet
    0.65
    itudinal
    0.65
    Activations Density 1.112%

    No Known Activations