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. 772
    Prev
    Next
    INDEX
    Explanations

    a mix of government/military actions, numbers, and present tense verbs.

    oai_token-act-pair · gemini-2.0-flash

    sending or fielding

    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
     EdgeInsets
    -0.68
     BrowserModule
    -0.65
    expandindo
    -0.65
     BaseActivity
    -0.61
    BeginInit
    -0.60
     BorderRadius
    -0.58
    abetes
    -0.58
     StatefulWidget
    -0.57
    WithIdentifier
    -0.55
    itoria
    -0.51
    POSITIVE LOGITS
    állítás
    0.62
    tská
    0.55
    OUBLE
    0.52
     което
    0.52
     betale
    0.50
    Lähteet
    0.49
     mengirimkan
    0.49
     stä
    0.48
     dieną
    0.48
    bringung
    0.47
    Activations Density 1.295%

    No Known Activations