© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3491
    Prev
    Next
    INDEX
    Explanations

    technical documentation and specifications related to inventions, wiring, and manufacturing.

    oai_token-act-pair · gemini-2.0-flash

    plurality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     RSSSF
    -0.81
     fubject
    -0.62
    bootstrapcdn
    -0.62
    DrawerLayout
    -0.62
    uminense
    -0.60
     Zanzibar
    -0.60
    SwitchCompat
    -0.60
     ftate
    -0.59
     ſtate
    -0.59
    lapsingToolbar
    -0.59
    POSITIVE LOGITS
     INVENTION
    1.00
    odiment
    0.98
     Patent
    0.85
     embodiments
    0.85
    CppMethod
    0.80
    例文帳に追加
    0.79
     PATENT
    0.79
    SourceChecksum
    0.77
    Patent
    0.77
     localObject
    0.76
    Activations Density 4.306%

    No Known Activations