© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9832
    Prev
    Next
    INDEX
    Explanations

    what appear to be acronyms, math symbols/equations, and medical terminology

    oai_token-act-pair · gemini-2.0-flash

    Technical/formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    SequentialGroup
    -0.91
     AssemblyVersion
    -0.90
    parsedMessage
    -0.88
    OGND
    -0.88
    NameInMap
    -0.85
    featureID
    -0.83
    HostException
    -0.83
    InjectAttribute
    -0.81
    LookAnd
    -0.81
     autorytatywna
    -0.80
    POSITIVE LOGITS
     z
    0.38
    bu
    0.38
     vPvB
    0.36
    Corn
    0.36
    z
    0.35
    Rourke
    0.34
     specification
    0.34
     корпуса
    0.34
    แห่ง
    0.33
    ka
    0.33
    Activations Density 0.370%

    No Known Activations