© 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. 2433
    Prev
    Next
    INDEX
    Explanations

    mentions of "this" or "the" along with other positive descriptive words or brands.

    oai_token-act-pair · gemini-2.0-flash

    This

    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
     originals
    -0.54
     Saltar
    -0.50
    IsRequired
    -0.48
    Kontrola
    -0.47
     sarili
    -0.45
    QtWidgets
    -0.45
     îna
    -0.44
     Nationale
    -0.44
    VIRONMENT
    -0.44
    Források
    -0.44
    POSITIVE LOGITS
    RegressionTest
    0.70
    MigrationBuilder
    0.68
    Tembelea
    0.65
    '])->
    0.64
     дописавши
    0.64
    )");
    0.64
    ValueStyle
    0.62
     Normdatei
    0.61
    aarrggbb
    0.59
    يميديا
    0.59
    Activations Density 4.343%

    No Known Activations