© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15397
    Prev
    Next
    INDEX
    Explanations

    references to food and time

    oai_token-act-pair · gemini-2.0-flash

    numerical expressions related to time

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

    minute, minuten, Minute

    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
    Negative Logits
     hours
    -1.10
     Hours
    -0.99
     hour
    -0.97
     two
    -0.96
     Hour
    -0.94
     Two
    -0.93
    Two
    -0.89
    Hour
    -0.88
    hour
    -0.88
     horas
    -0.87
    POSITIVE LOGITS
     ten
    0.79
    Rhestr
    0.69
    Ten
    0.68
     Ten
    0.66
     виправивши
    0.64
    ConstraintMaker
    0.64
    minute
    0.62
     minuten
    0.62
    Minute
    0.60
     AssemblyCulture
    0.60
    Activations Density 1.590%

    No Known Activations