© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5647
    Prev
    Next
    INDEX
    Explanations

    text containing phrases like "is that", "has to", "is to", or "is when"

    oai_token-act-pair · gemini-2.0-flash

    diverse excerpts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    انيف
    -0.49
    /*
    -0.47
    //
    -0.44
    *>(
    -0.42
     and
    -0.42
     <",
    -0.42
    Autoritní
    -0.41
    phylo
    -0.40
    '])){
    -0.40
    <?=
    -0.40
    POSITIVE LOGITS
     betweenstory
    0.75
    WriteTagHelper
    0.63
     dilution
    0.62
    setNum
    0.62
    出版年
    0.61
     mixte
    0.61
    ➌
    0.60
     briefed
    0.60
    quantidade
    0.60
    twimg
    0.59
    Activations Density 11.165%

    No Known Activations