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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13392
    Prev
    Next
    INDEX
    Explanations

    temporal words like "day" and "during"

    oai_token-act-pair · gemini-2.0-flash

    say "day"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    -2.08
     night
    -2.05
    Day
    -2.03
     DAY
    -1.90
     Night
    -1.90
    DAY
    -1.89
     day
    -1.82
    day
    -1.81
    Night
    -1.81
     morning
    -1.78
    POSITIVE LOGITS
    ỏi
    0.45
    etal
    0.40
     annehmen
    0.39
     vivement
    0.38
    ijiet
    0.38
     dips
    0.36
    ovács
    0.36
    askins
    0.36
    
    0.36
    di
    0.35
    Activations Density 1.261%

    No Known Activations