© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12700
    Prev
    Next
    INDEX
    Explanations

    words associated with requests and high demand

    oai_token-act-pair · gemini-2.0-flash

    requests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     U
    -0.51
     R
    -0.51
     Sub
    -0.50
     sub
    -0.50
    CrossRef
    -0.47
     Ba
    -0.46
     Mark
    -0.46
    <eos>
    -0.45
     both
    -0.43
     Level
    -0.43
    POSITIVE LOGITS
    IntoConstraints
    0.86
    contentLoaded
    0.78
    ThroughAttribute
    0.69
     Numerade
    0.68
    IUrlHelper
    0.67
    bitField
    0.67
    +:+
    0.66
    WithIOException
    0.65
     referenties
    0.65
    SequentialGroup
    0.65
    Activations Density 2.041%

    No Known Activations