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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2417
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate causation or attribution.

    oai_token-act-pair · gemini-2.0-flash

    causality

    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
    Assista
    -0.53
    zionato
    -0.51
    Conclusão
    -0.49
    stopPropagation
    -0.49
     Тро
    -0.48
    ljiv
    -0.47
    çadas
    -0.47
    腈
    -0.47
     myſelf
    -0.47
    veja
    -0.47
    POSITIVE LOGITS
    tagHelperRunner
    0.79
    ftagPool
    0.68
    IsContent
    0.65
    MeasureSpec
    0.65
    dafx
    0.63
     Exacts
    0.63
    RegistryLite
    0.60
    SequentialGroup
    0.58
     getopt
    0.57
    UnsafeEnabled
    0.57
    Activations Density 12.000%

    No Known Activations