© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11937
    Prev
    Next
    INDEX
    Explanations

    the letter G followed by a number or a word for a line in a graph

    oai_token-act-pair · gemini-2.0-flash

    G

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    G
    -1.75
    g
    -1.20
     g
    -0.93
    <bos>
    -0.84
     G
    -0.71
    Gs
    -0.68
    T
    -0.67
    K
    -0.67
    P
    -0.65
    B
    -0.64
    POSITIVE LOGITS
    :✨
    0.75
    lloworld
    0.72
    queryInterface
    0.71
    enumii
    0.68
    WriteTagHelper
    0.67
    SpringBootTest
    0.66
    ResponseWriter
    0.66
     autorytatywna
    0.65
    ValueStyle
    0.65
    ArrayAdapter
    0.63
    Activations Density 0.723%

    No Known Activations