© 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. 7447
    Prev
    Next
    INDEX
    Explanations

    the word "the" preceded and followed by words related to time, seasons, or events.

    oai_token-act-pair · gemini-2.0-flash

    terms related to time and seasons

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

    the

    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
    -0.63
     Day
    -0.62
    day
    -0.59
    Życiorys
    -0.56
    andaag
    -0.53
     day
    -0.52
     DAY
    -0.49
    那天
    -0.48
    DAY
    -0.47
    đu
    -0.47
    POSITIVE LOGITS
     year
    1.70
     season
    1.69
    season
    1.36
    year
    1.30
     SEASON
    1.23
     YEAR
    1.21
    Season
    1.19
     Season
    1.16
     semester
    1.16
     Year
    1.13
    Activations Density 1.718%

    No Known Activations