© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13022
    Prev
    Next
    INDEX
    Explanations

    references to age or time in someone's life

    oai_token-act-pair · gemini-2.0-flash

    time indicators and ages

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

    was

    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
     للمعارف
    -1.06
    ^(@)
    -1.05
     itſelf
    -1.01
     виправивши
    -0.93
    DoubleQuotes
    -0.92
     ―――――
    -0.91
     myſelf
    -0.90
    Diwedd
    -0.90
     becauſe
    -0.89
     Theſe
    -0.88
    POSITIVE LOGITS
     seven
    0.73
     six
    0.68
     a
    0.67
     eight
    0.66
     five
    0.65
     nine
    0.60
     three
    0.59
     in
    0.59
     four
    0.59
     two
    0.53
    Activations Density 1.232%

    No Known Activations