© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13195
    Prev
    Next
    INDEX
    Explanations

    dates and scientific words related to the history of human inventions

    oai_token-act-pair · gemini-2.0-flash

    Describing inventions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    WebpackPlugin
    -0.70
     Italijani
    -0.69
    //
    -0.68
     BoxDecoration
    -0.68
     AssemblyCompany
    -0.65
     يتيمه
    -0.64
     BoxFit
    -0.59
    :✨
    -0.58
     ComVisible
    -0.57
     viewDidLoad
    -0.57
    POSITIVE LOGITS
    ORIAL
    0.50
     patching
    0.49
    anyan
    0.48
     chain
    0.47
    phere
    0.47
     pier
    0.47
    RIQUE
    0.46
    ypep
    0.46
     recording
    0.46
     drop
    0.46
    Activations Density 2.945%

    No Known Activations