© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6696
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to something acting or working as something else

    oai_token-act-pair · gemini-2.0-flash

    act

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    stdc
    -0.59
    closed
    -0.54
     defaultstate
    -0.50
    XmlAccessorType
    -0.49
    Geografie
    -0.47
     AssemblyCulture
    -0.46
     quelconque
    -0.45
    owned
    -0.45
    URLConnection
    -0.45
    closing
    -0.45
    POSITIVE LOGITS
    UnsafeEnabled
    0.69
    исленность
    0.67
    WireFormatLite
    0.66
    iprot
    0.62
    SerializedSize
    0.61
    IUrlHelper
    0.60
    tagHelperRunner
    0.60
     Biôgrafia
    0.57
    arraycopy
    0.57
     asynchronously
    0.57
    Activations Density 1.644%

    No Known Activations