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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11225
    Prev
    Next
    INDEX
    Explanations

    words related to management, healthcare, and recreational activities

    oai_token-act-pair · gemini-2.0-flash

    concepts of coherence and belonging

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

    work education health policies

    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
    MemoryWarning
    -0.89
    RegistryLite
    -0.78
     définiti
    -0.75
     commerciaux
    -0.74
     financières
    -0.72
     وتسجيلات
    -0.71
    makeText
    -0.68
     récents
    -0.68
     pinulongan
    -0.67
     defaultstate
    -0.66
    POSITIVE LOGITS
     coherence
    0.48
    tvguidetime
    0.46
     reflexion
    0.46
    <bos>
    0.46
    &
    0.43
     belonging
    0.43
     ​​
    0.42
     коло
    0.42
     parach
    0.42
     rhythm
    0.41
    Activations Density 5.167%

    No Known Activations