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. 1196
    Prev
    Next
    INDEX
    Explanations

    the digit 2 followed by a zero

    oai_token-act-pair · gemini-2.0-flash

    2

    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
     (
    -0.77
    ,
    -0.71
    ↵
    -0.64
    :
    -0.59
    ↵↵
    -0.58
    .
    -0.57
     "
    -0.56
     [
    -0.54
     ...
    -0.54
    ;
    -0.53
    POSITIVE LOGITS
    <bos>
    3.13
     Савезне
    1.84
    tagHelperRunner
    1.60
     Мексичка
    1.58
     мәкал
    1.55
     autorytatywna
    1.53
    Personendaten
    1.48
     Paglinawan
    1.48
    Билгалдахарш
    1.48
    ########.
    1.46
    Activations Density 0.003%

    No Known Activations