© 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. 10464
    Prev
    Next
    INDEX
    Explanations

    places where there appears to be code

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "rate"

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

    contains "ate"

    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
    SequentialGroup
    -0.70
     مُعرِّف
    -0.53
     Ono
    -0.52
    AllowUser
    -0.52
    ávajú
    -0.51
    typeparam
    -0.48
    ifica
    -0.48
     بحر
    -0.48
    agerie
    -0.47
     Belf
    -0.47
    POSITIVE LOGITS
     rate
    0.74
    rate
    0.69
     ate
    0.69
    RATE
    0.66
    laten
    0.65
    Rate
    0.61
    ateg
    0.61
     Rate
    0.61
    atea
    0.59
    maten
    0.59
    Activations Density 1.058%

    No Known Activations