© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3801
    Prev
    Next
    INDEX
    Explanations

    references to time in the recent past, specifically using the words "last" or "past" combined with "few", "several", or a number of years

    oai_token-act-pair · gemini-2.0-flash

    Past time

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     فريبيس
    -0.77
     تضيفلها
    -0.70
     مشين
    -0.60
     Theſe
    -0.60
     Houſe
    -0.59
    Vidite
    -0.59
     varandra
    -0.59
     المعيارى
    -0.58
     erbjud
    -0.58
     œufs
    -0.57
    POSITIVE LOGITS
     year
    0.73
     
    0.62
    出版年
    0.55
     century
    0.49
     z
    0.49
     y
    0.48
    ankar
    0.47
    dcc
    0.47
    MIDDLEWARE
    0.46
     censo
    0.45
    Activations Density 1.171%

    No Known Activations