© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15935
    Prev
    Next
    INDEX
    Explanations

    various ways to use a keyboard to control GUI elements

    oai_token-act-pair · gemini-2.0-flash

    Code and keyboard commands

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    //
    -0.65
    TypedDataSet
    -0.54
     Ramon
    -0.54
    ]++;
    -0.54
    NSON
    -0.52
    chromedriver
    -0.52
     reference
    -0.50
    kháu
    -0.49
     Guy
    -0.49
     Reference
    -0.49
    POSITIVE LOGITS
     ContentValues
    0.75
     betweenstory
    0.59
     kasarigan
    0.58
     resourceCulture
    0.57
     AssemblyCulture
    0.56
    География
    0.52
    JScrollPane
    0.49
     OGSÅ
    0.49
    XmlAccessorType
    0.49
    Witam
    0.48
    Activations Density 1.261%

    No Known Activations