© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1128
    Prev
    Next
    INDEX
    Explanations

    Java code related to creating dialog boxes and interacting with image selection intents

    oai_token-act-pair · gemini-2.0-flash

    code variables

    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
    <bos>
    -0.52
    <eos>
    -0.50
    RegressionTest
    -0.38
     call
    -0.36
     este
    -0.36
     geb
    -0.36
     y
    -0.35
     b
    -0.35
     um
    -0.34
     calls
    -0.34
    POSITIVE LOGITS
     MainAxisSize
    0.91
    principalTable
    0.88
    UserScript
    0.87
    HomeAsUpEnabled
    0.83
    TagMode
    0.81
     resourceCulture
    0.80
    parsedMessage
    0.79
     Theſe
    0.77
    XmlAccessType
    0.75
     Jefus
    0.71
    Activations Density 1.942%

    No Known Activations