© 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. 6953
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "the" followed by words like "day" or prepositions such as "of" or "at."

    oai_token-act-pair · gemini-2.0-flash

    variations of the word 'day'

    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
    season
    -0.79
     season
    -0.77
    Season
    -0.74
    Искәрмәләр
    -0.73
    اریخ
    -0.68
     defStyle
    -0.68
    verwijspagina
    -0.67
     year
    -0.66
    Externí
    -0.65
     Season
    -0.64
    POSITIVE LOGITS
     day
    0.82
    day
    0.68
     night
    0.63
     DAY
    0.59
     days
    0.57
    DAY
    0.56
     laugh
    0.56
     lift
    0.52
    days
    0.52
     Day
    0.52
    Activations Density 1.642%

    No Known Activations