© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2395
    Prev
    Next
    INDEX
    Explanations

    phrases using "to date" indicating the limit of current knowledge or progress

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "date"

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

    to

    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
     negli
    -0.58
     ")";
    -0.51
    (""));
    -0.50
     viewHolder
    -0.50
    近
    -0.48
     "];
    -0.48
     arşivlendi
    -0.48
    ))[
    -0.48
    zegor
    -0.47
    thanx
    -0.47
    POSITIVE LOGITS
     date
    2.06
    date
    1.66
     Date
    1.55
     DATE
    1.45
    Date
    1.38
     dates
    1.36
     Dates
    1.21
    DATE
    1.18
    dates
    1.13
     DATES
    1.09
    Activations Density 1.162%

    No Known Activations