© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2744
    Prev
    Next
    INDEX
    Explanations

    code changes or diffs in software, especially patch files

    oai_token-act-pair · gemini-2.0-flash

    code lines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    DockStyle
    -0.84
    SequentialGroup
    -0.75
    日閲覧
    -0.73
     estekak
    -0.69
    ArrowToggle
    -0.68
    Попис
    -0.68
    انيف
    -0.67
     оригіналу
    -0.65
    TestingModule
    -0.64
    !*\
    -0.63
    POSITIVE LOGITS
    াহ
    0.40
    boot
    0.39
     customer
    0.37
    ESS
    0.37
    ustomer
    0.37
    Customer
    0.37
    線の
    0.36
    ushan
    0.36
     alinea
    0.35
    Bagh
    0.35
    Activations Density 2.753%

    No Known Activations