© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10601
    Prev
    Next
    INDEX
    Explanations

    references to defined or arbitrary boundaries or limits

    oai_token-act-pair · gemini-2.0-flash

    lines and boundaries

    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
    XmlType
    -0.65
     allmän
    -0.59
     financières
    -0.55
     materialen
    -0.52
     mű
    -0.50
     magát
    -0.50
     pály
    -0.49
     väh
    -0.49
     hvě
    -0.49
     âgées
    -0.48
    POSITIVE LOGITS
    Autoritní
    0.74
    nière
    0.73
    Rhestr
    0.68
     boundaries
    0.62
     Boundaries
    0.61
     saites
    0.59
    ViewFeatures
    0.59
    ритори
    0.58
     demar
    0.58
    sbericht
    0.56
    Activations Density 1.088%

    No Known Activations