© 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. 10263
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and equations along with related terms

    oai_token-act-pair · gemini-2.0-flash

    partial

    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
    partial
    -1.08
    Partial
    -0.87
     partial
    -0.85
     Partial
    -0.82
    <bos>
    -0.70
    ∂
    -0.69
     parcial
    -0.67
     partielle
    -0.66
    MENAFN
    -0.55
    CppCodeGen
    -0.54
    POSITIVE LOGITS
    énario
    0.64
     inflater
    0.63
     onCreateView
    0.60
    Coordonnées
    0.58
     pinulongan
    0.57
    Bibliograf
    0.55
    انيف
    0.54
     Mor
    0.54
    NewUrlParser
    0.54
    includegraphics
    0.54
    Activations Density 9.187%

    No Known Activations