© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14903
    Prev
    Next
    INDEX
    Explanations

    words related to computer hardware and plumbing

    oai_token-act-pair · gemini-2.0-flash

    onet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    vite
    -0.50
    MessageOf
    -0.50
    calyp
    -0.47
    TestTools
    -0.47
    الإنجليزية
    -0.46
    Moved
    -0.46
    move
    -0.45
    sweep
    -0.45
    antie
    -0.44
     Move
    -0.44
    POSITIVE LOGITS
    TagMode
    0.61
     kaarangay
    0.58
    AddTagHelper
    0.57
    UserScript
    0.55
     otomatig
    0.53
     الرياضيه
    0.52
    XmlType
    0.51
    lapsingToolbar
    0.50
    ISupport
    0.49
    WebServlet
    0.49
    Activations Density 1.882%

    No Known Activations