© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6360
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to control, medicine, and content providing systems, especially relating to pharmaceutical and air conditioning contexts.

    oai_token-act-pair · gemini-2.0-flash

    legal/business documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    expandindo
    -0.57
     ujednoznacz
    -0.54
    MENAFN
    -0.52
     noten
    -0.50
     gli
    -0.49
     boca
    -0.48
     grig
    -0.47
    nser
    -0.46
    enterOuterAlt
    -0.46
     للمعارف
    -0.46
    POSITIVE LOGITS
    ksikon
    0.62
    setVerticalGroup
    0.62
    complexContent
    0.60
    PrototypeOf
    0.59
    WebVitals
    0.59
     AttributeSet
    0.57
     Shakspeare
    0.57
    ambahkan
    0.56
    tagHelperRunner
    0.56
    EndInit
    0.56
    Activations Density 1.281%

    No Known Activations