© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12659
    Prev
    Next
    INDEX
    Explanations

    name-like strings ending in "ine" or "ia"

    oai_token-act-pair · gemini-2.0-flash

    Legal/technical documents

    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
    RegressionTest
    -0.83
    WriteTagHelper
    -0.79
    はじめに
    -0.74
    :✨
    -0.74
     Numerade
    -0.70
     <>",
    -0.67
    WireFormatLite
    -0.66
    ILayout
    -0.66
     AssemblyCulture
    -0.66
    StructEnd
    -0.65
    POSITIVE LOGITS
     ti
    1.12
    ti
    1.02
     Ti
    0.95
    Ti
    0.89
    ティ
    0.82
    tik
    0.80
    tis
    0.77
    TI
    0.76
    tig
    0.75
    tid
    0.74
    Activations Density 0.234%

    No Known Activations