© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12697
    Prev
    Next
    INDEX
    Explanations

    words associated with the functionality and design of holding devices

    oai_token-act-pair · gemini-2.0-flash

    holder

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     consecutive
    -0.62
     continuous
    -0.58
     kasarigan
    -0.52
     contin
    -0.52
     jsPsych
    -0.49
    amation
    -0.48
    IContainer
    -0.47
    arini
    -0.47
     continuously
    -0.46
    avadoc
    -0.46
    POSITIVE LOGITS
    Jereo
    0.69
    ChildScrollView
    0.69
     ujednoznacz
    0.65
     lenker
    0.60
     OFDb
    0.56
     TextAppearance
    0.56
    談社
    0.55
     bezeichneter
    0.55
    CppCodeGen
    0.54
     sumpay
    0.54
    Activations Density 1.028%

    No Known Activations