© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11624
    Prev
    Next
    INDEX
    Explanations

    the string "app" at the beginning of a word

    oai_token-act-pair · gemini-2.0-flash

    forms of the word "app"

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

    app

    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
     [
    -0.43
     ((
    -0.41
    fer
    -0.41
     son
    -0.38
    hline
    -0.38
     T
    -0.38
    freopen
    -0.38
     -
    -0.37
    copo
    -0.36
     
    -0.36
    POSITIVE LOGITS
     itſelf
    0.99
     myſelf
    0.96
     himſelf
    0.91
     cauſe
    0.90
     Majefty
    0.89
     raiſ
    0.87
     Jefus
    0.87
     ſever
    0.86
    writeFieldEnd
    0.86
     للمعارف
    0.86
    Activations Density 0.480%

    No Known Activations