© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3439
    Prev
    Next
    INDEX
    Explanations

    acronyms, especially those related to physics, networking, or biology and chemistry

    oai_token-act-pair · gemini-2.0-flash

    (

    np_max-act · gemini-2.0-flash

    (

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    /*---
    -0.47
     MaterialApp
    -0.47
    "]();
    -0.47
    béco
    -0.46
    audiovisuel
    -0.44
     opérateur
    -0.44
    OIR
    -0.43
     assurent
    -0.42
     strany
    -0.41
     έκ
    -0.41
    POSITIVE LOGITS
    RenderAtEndOf
    0.80
    <bos>
    0.67
    WireFormatLite
    0.66
     /\.(
    0.64
     AssemblyCompany
    0.64
    TagHelper
    0.63
    kloped
    0.62
    XHR
    0.62
    gesetzt
    0.59
     &___
    0.59
    Activations Density 1.958%

    No Known Activations