© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12479
    Prev
    Next
    INDEX
    Explanations

    C++ code snippets, especially those involving vectors, strings, or templates

    oai_token-act-pair · gemini-2.0-flash

    vector

    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
     vector
    -2.28
     Vector
    -2.16
    vector
    -2.16
    Vector
    -2.06
     vectors
    -1.88
     VECTOR
    -1.84
     Vectors
    -1.81
     vektor
    -1.61
    vectors
    -1.61
    VECTOR
    -1.60
    POSITIVE LOGITS
    coque
    0.50
     عشر
    0.48
    usercontent
    0.47
     عش
    0.47
     kese
    0.46
    kém
    0.46
     resourceCulture
    0.44
    templ
    0.44
     excru
    0.44
    必
    0.43
    Activations Density 8.041%

    No Known Activations