Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 16-GEMMASCOPE-TRANSCODER-16K
    4. 1046
    Prev
    Next
    INDEX
    Explanations

    words starting with "ly" that are rooted in medicine or science

    oai_token-act-pair · gemini-2.0-flash

    words with "ly" in them

    np_token-act-pair-logits · gemini-2.0-flash

    Lycium

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.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
     mondi
    -0.41
    bitkan
    -0.40
    zboi
    -0.40
    万美元
    -0.40
     bevis
    -0.40
    var
    -0.40
     parha
    -0.39
     pulumi
    -0.38
     personnalisés
    -0.38
     Henry
    -0.37
    POSITIVE LOGITS
    MarshalTo
    0.69
    Rhestr
    0.65
    makeConstraints
    0.64
    ImageContext
    0.62
    Yours
    0.60
    webElement
    0.60
    GOTREF
    0.59
    ToBounds
    0.58
    chee
    0.57
    WithMany
    0.57
    Activations Density 1.073%

    No Known Activations