© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4330
    Prev
    Next
    INDEX
    Explanations

    the 'Add' method

    oai_token-act-pair · gemini-2.0-flash

    Add

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    脚注の使い方
    -1.12
    MigrationBuilder
    -1.11
     дописавши
    -1.09
     ویکی‌پدیای
    -1.05
    StoryboardSegue
    -1.04
    RegressionTest
    -0.97
     resourceCulture
    -0.96
    webElementXpaths
    -0.92
    GraphicsUnit
    -0.91
     Paglinawan
    -0.89
    POSITIVE LOGITS
     
    0.47
    _{*
    0.46
    </em>
    0.46
    ıs
    0.45
    {\
    0.45
     logiciel
    0.45
     bày
    0.43
    _{*}
    0.43
    </i>
    0.43
    ınd
    0.43
    Activations Density 0.025%

    No Known Activations