© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10385
    Prev
    Next
    INDEX
    Explanations

    the beginning of the word "fool" and "follow"

    oai_token-act-pair · gemini-2.0-flash

    fo

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    <tbody>
    -0.57
    <thead>
    -0.56
    ocarpus
    -0.55
    PackageManager
    -0.54
    untergang
    -0.52
     OkHttpClient
    -0.52
    BrowserModule
    -0.52
    uests
    -0.49
    ifolium
    -0.49
     üzer
    -0.49
    POSITIVE LOGITS
    BeginContext
    0.61
     lenker
    0.59
    ReusableCell
    0.54
    parsedMessage
    0.54
    Билгалдахарш
    0.52
    IVEREF
    0.51
    expandindo
    0.50
    Datuak
    0.49
    KommentareTeilen
    0.49
     Beweis
    0.48
    Activations Density 0.438%

    No Known Activations