© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12654
    Prev
    Next
    INDEX
    Explanations

    code-related terms related to data storage, decoding, and messaging

    oai_token-act-pair · gemini-2.0-flash

    let

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    一本
    -0.47
    ETY
    -0.46
     Tri
    -0.45
    valueOf
    -0.43
    bered
    -0.42
    holt
    -0.41
    ölt
    -0.41
    dies
    -0.41
     Bal
    -0.40
    quina
    -0.40
    POSITIVE LOGITS
     purpoſe
    1.04
     ſtate
    0.87
     ſche
    0.86
     pleaſure
    0.84
     الرياضيه
    0.83
     myſelf
    0.82
    ftagPool
    0.81
     Jefus
    0.81
     ویکی‌پدیای
    0.78
     houſe
    0.78
    Activations Density 22.641%

    No Known Activations