© 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. 12736
    Prev
    Next
    INDEX
    Explanations

    a mix of code snippets, Spanish words, and network/protocol related terms

    oai_token-act-pair · gemini-2.0-flash

    code and foreign language

    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
     Cook
    -0.49
     port
    -0.46
    zeczytaj
    -0.45
    latLng
    -0.43
     med
    -0.42
    LayoutPanel
    -0.42
     cook
    -0.41
     mat
    -0.41
    endphp
    -0.41
    sprechend
    -0.41
    POSITIVE LOGITS
    rawDesc
    0.82
     &___
    0.71
     jspb
    0.70
    مصادر
    0.66
    XmlAccessType
    0.65
    ModelAdmin
    0.64
     FetchType
    0.59
     marbre
    0.58
     linkovi
    0.57
     fieldNum
    0.56
    Activations Density 1.407%

    No Known Activations