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. 7-GEMMASCOPE-TRANSCODER-16K
    4. 6969
    Prev
    Next
    INDEX
    Explanations

    disclaimers of responsibility and limitation of legal liability.

    oai_token-act-pair · gemini-2.0-flash

    responsible

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     intptr
    -0.54
    ثيق
    -0.43
    OnLoad
    -0.43
    blob
    -0.42
    ず
    -0.41
    teln
    -0.40
    ocar
    -0.40
    HtmlAttribute
    -0.40
    coun
    -0.40
    NSNotification
    -0.40
    POSITIVE LOGITS
    StoryboardSegue
    0.69
     للاسماء
    0.68
     lenker
    0.67
     виправивши
    0.62
    niająca
    0.62
    cloudflare
    0.62
    ParallelGroup
    0.61
    binant
    0.57
    epam
    0.57
     nahilalakip
    0.56
    Activations Density 0.284%

    No Known Activations