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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14954
    Prev
    Next
    INDEX
    Explanations

    clauses separated by commas, conjunctions, and punctuation in film reviews.

    oai_token-act-pair · gemini-2.0-flash

    quotation marks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    ?}",
    -0.68
     Administrativna
    -0.62
     nahilalakip
    -0.62
    __':
    
    -0.60
    )");
    
    -0.60
     depositphotos
    -0.60
     Walkover
    -0.59
    انجليز
    -0.58
    يكب
    -0.57
    $.
    
    -0.55
    POSITIVE LOGITS
     "
    1.71
     “
    1.66
    「
    1.59
     «
    1.48
     „
    1.42
     「
    1.41
    ,「
    1.38
    、「
    1.33
    ,“
    1.31
     ‘‘
    1.29
    Activations Density 0.814%

    No Known Activations