© 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
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9523
    Prev
    Next
    INDEX
    Explanations

    words related to engineering tasks, especially those involving design, materials, and possibly NASA

    oai_token-act-pair · gemini-2.0-flash

    Random, varied text snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    Rhestr
    -0.57
     Infórmanos
    -0.48
    Primitives
    -0.47
    rentices
    -0.47
     addUser
    -0.45
    iki
    -0.43
    attempt
    -0.42
    xelles
    -0.42
    NameInMap
    -0.41
    صیلات
    -0.41
    POSITIVE LOGITS
    ChildScrollView
    0.99
    Personendaten
    0.85
    Hochspringen
    0.77
    MLLoader
    0.74
    stdc
    0.73
    RectangleBorder
    0.72
     становника
    0.67
    Jegyzetek
    0.66
     HttpNotFound
    0.66
    ReusableCell
    0.65
    Activations Density 1.512%

    No Known Activations