© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15338
    Prev
    Next
    INDEX
    Explanations

    lists of online publications

    oai_token-act-pair · gemini-2.0-flash

    News/journalistic writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    Magento
    -0.52
    Artik
    -0.48
    Atoi
    -0.45
    FilterChain
    -0.43
    Subjects
    -0.43
    pok
    -0.42
    peli
    -0.42
     članak
    -0.42
    aarrggbb
    -0.42
    Annette
    -0.42
    POSITIVE LOGITS
     AssemblyTitle
    0.91
     kasarigan
    0.70
    ]--;
    0.69
     mergeFrom
    0.68
     WebDriverWait
    0.66
    noinspection
    0.65
    ousand
    0.64
    ManagedBean
    0.63
     Alembic
    0.63
    RunAsync
    0.63
    Activations Density 0.558%

    No Known Activations