© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1564
    Prev
    Next
    INDEX
    Explanations

    the phrase "couple of [time period]" or similar constructions indicating a short period of time

    oai_token-act-pair · gemini-2.0-flash

    phrases indicating time duration or intervals

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

    couple

    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
    Negative Logits
    Демографія
    -0.87
     Wikimedijinoj
    -0.74
    évaluateur
    -0.71
     wireType
    -0.69
     EconPapers
    -0.69
    expandindo
    -0.69
    ValueStyle
    -0.68
     vœux
    -0.68
    OGND
    -0.67
    RectangleBorder
    -0.66
    POSITIVE LOGITS
     of
    0.82
     non
    0.50
     day
    0.48
    ye
    0.45
    day
    0.45
    ATTER
    0.43
     month
    0.42
     bits
    0.42
     week
    0.42
    سین
    0.41
    Activations Density 0.393%

    No Known Activations