© 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. 13103
    Prev
    Next
    INDEX
    Explanations

    mentions of time, particularly years and months

    oai_token-act-pair · gemini-2.0-flash

    Mentions years

    np_max-act-logits · gemini-2.0-flash

    say "year/month"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     year
    -2.19
     Year
    -1.88
    Year
    -1.88
     month
    -1.84
     YEAR
    -1.80
    year
    -1.80
     years
    -1.66
    YEAR
    -1.66
     Month
    -1.59
     week
    -1.53
    POSITIVE LOGITS
     MotionEvent
    0.59
    újo
    0.55
    DJANGO
    0.52
    angering
    0.50
     Scy
    0.50
    mes
    0.50
     createSlice
    0.50
    scriptcase
    0.49
     backing
    0.48
    MES
    0.47
    Activations Density 1.468%

    No Known Activations