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. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7274
    Prev
    Next
    INDEX
    Explanations

    time and ordinal numbers, sometimes combined with other units of measure

    oai_token-act-pair · gemini-2.0-flash

    time and years

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    addCriterion
    -0.73
     typelib
    -0.71
    WebVitals
    -0.71
    EndContext
    -0.71
    帖最后由
    -0.68
     defaultstate
    -0.67
     MessageBoxIcon
    -0.66
     resourceCulture
    -0.65
     snippetHide
    -0.63
     дописавши
    -0.62
    POSITIVE LOGITS
     hours
    0.61
     Hours
    0.56
     hour
    0.54
    hours
    0.54
     Minutes
    0.51
    uspiel
    0.50
     first
    0.50
     minutes
    0.50
    Hours
    0.48
    Heraus
    0.48
    Activations Density 2.052%

    No Known Activations