© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 3-GEMMASCOPE-TRANSCODER-16K
    4. 9522
    Prev
    Next
    INDEX
    Explanations

    technical information about signals, circuits, and data acquisition, possibly for analysis

    oai_token-act-pair · gemini-2.0-flash

    circuit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    exp
    -0.59
     acquisition
    -0.54
     Acquisition
    -0.52
     statute
    -0.47
     acquire
    -0.46
    Acquisition
    -0.46
    Exp
    -0.45
    stat
    -0.45
     acquired
    -0.45
     acquiring
    -0.45
    POSITIVE LOGITS
     CreateTagHelper
    1.22
    Personensuche
    1.13
     autorytatywna
    1.01
    MLLoader
    0.96
     AssemblyCulture
    0.96
     estekak
    0.90
     referenties
    0.89
    contentLoaded
    0.88
     bezeichneter
    0.88
    expandindo
    0.87
    Activations Density 10.857%

    No Known Activations