Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 10944
    Prev
    Next
    INDEX
    Explanations

    times of day written in numbers

    oai_token-act-pair · gemini-2.0-flash

    tokens related to time or scheduling

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

    Numerical times

    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
     saucer
    -0.68
    ThroughAttribute
    -0.64
     initComponents
    -0.63
    ^(@)
    -0.63
     تانيه
    -0.61
     насељу
    -0.61
    ]")]
    -0.60
    ViewFeatures
    -0.60
    AddTagHelper
    -0.60
     دیکھیے
    -0.59
    POSITIVE LOGITS
     o
    0.56
     O
    0.50
     EconPapers
    0.45
    Enllaces
    0.44
    accor
    0.41
    :
    0.41
     system
    0.41
     ocio
    0.40
    cmu
    0.40
    eden
    0.39
    Activations Density 1.126%

    No Known Activations