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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8139
    Prev
    Next
    INDEX
    Explanations

    references to people, political parties and legal codes

    oai_token-act-pair · gemini-2.0-flash

    person

    np_max-act · gemini-2.0-flash

    persons

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    iterranée
    -0.57
    MethodManager
    -0.56
    بية
    -0.54
     noexcept
    -0.52
     Meli
    -0.50
    uerre
    -0.50
     Ety
    -0.49
     huesos
    -0.49
     потому
    -0.48
    ObjectId
    -0.48
    POSITIVE LOGITS
    <bos>
    0.83
    awtextra
    0.74
    expandindo
    0.64
    onViewCreated
    0.64
     betweenstory
    0.64
    verwijspagina
    0.63
     Савезне
    0.60
    LikeLike
    0.60
    tanleria
    0.58
     autorytatywna
    0.57
    Activations Density 0.770%

    No Known Activations