© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2191
    Prev
    Next
    INDEX
    Explanations

    technical words or acronyms related to a particular domain

    oai_token-act-pair · gemini-2.0-flash

    Kingston borough, Facebook details

    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
    DotNetBar
    -0.58
     snow
    -0.52
    +:+
    -0.52
     SearchView
    -0.51
     {?>
    -0.49
    :✨
    -0.49
    ztály
    -0.49
     rumput
    -0.47
    jalá
    -0.47
     Snow
    -0.47
    POSITIVE LOGITS
     CreateTagHelper
    0.63
    NameInMap
    0.57
     elections
    0.54
    WireFormatLite
    0.54
    OGND
    0.53
    Begriffsklä
    0.52
     Existence
    0.51
     Elections
    0.51
     Himo
    0.50
    BaseActivity
    0.50
    Activations Density 15.802%

    No Known Activations