© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4035
    Prev
    Next
    INDEX
    Explanations

    log entries or lists with times and dates

    oai_token-act-pair · gemini-2.0-flash

    temporal references or time indicators

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

    Time measurements

    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
     rendez
    -0.47
     outputStream
    -0.43
    stens
    -0.43
     först
    -0.42
    bleau
    -0.42
    뀔
    -0.42
    nud
    -0.40
    íny
    -0.40
    뀐
    -0.40
    ه‌
    -0.39
    POSITIVE LOGITS
     day
    2.00
     Day
    1.94
    Day
    1.67
     DAY
    1.66
    day
    1.56
     week
    1.49
    DAY
    1.41
     Week
    1.32
     día
    1.25
     month
    1.23
    Activations Density 4.823%

    No Known Activations