© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10290
    Prev
    Next
    INDEX
    Explanations

    code snippets containing coordinate pairs and labels within parentheses and brackets

    oai_token-act-pair · gemini-2.0-flash

    Math equations and symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     Taxonomic
    -0.37
     flange
    -0.36
     funniest
    -0.36
     Taxes
    -0.35
     nase
    -0.34
     cutest
    -0.33
    warte
    -0.33
     Öffentlich
    -0.33
     раду
    -0.32
     horribly
    -0.32
    POSITIVE LOGITS
     AssemblyTitle
    0.94
    EndGlobalSection
    0.91
     kasarigan
    0.88
    ChildScrollView
    0.85
    Aiheesta
    0.81
    MigrationBuilder
    0.80
    دانشنامهٔ
    0.79
    principalTable
    0.77
    ValueStyle
    0.77
    argout
    0.77
    Activations Density 0.749%

    No Known Activations