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. 8-GEMMASCOPE-TRANSCODER-16K
    4. 1025
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with mathematics, writing, and the state of remaining the same.

    oai_token-act-pair · gemini-2.0-flash

    Changed or different states

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     هنوز
    -0.74
     still
    -0.71
    still
    -0.63
    Still
    -0.63
     fortfarande
    -0.62
     Still
    -0.61
     AssemblyProduct
    -0.61
    mybatisplus
    -0.58
    NoSuchAlgorithm
    -0.56
     ftill
    -0.56
    POSITIVE LOGITS
    ]]
    
    0.65
    "]);
    
    0.60
    []
    
    0.60
    GRANTED
    0.59
     chapter
    0.54
    )++;
    0.54
     مشين
    0.53
    "),
    
    0.52
    ")){
    
    0.51
    '),
    
    0.50
    Activations Density 5.876%

    No Known Activations