© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3684
    Prev
    Next
    INDEX
    Explanations

    symbols and units of measurement, alongside scientific vocabulary

    oai_token-act-pair · gemini-2.0-flash

    Scientific measurements and data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     vor
    -0.49
     há
    -0.45
    LOTTE
    -0.44
    وام
    -0.44
    =*/
    -0.44
     mu
    -0.44
    ╝
    -0.43
    loten
    -0.42
     lain
    -0.41
    دور
    -0.41
    POSITIVE LOGITS
     BrowserModule
    0.77
     Seeder
    0.72
     Efq
    0.71
     chert
    0.68
     doccia
    0.68
     aikaa
    0.68
    MigrationBuilder
    0.67
    AccessorTable
    0.67
     gravidanza
    0.67
    PerformLayout
    0.66
    Activations Density 10.747%

    No Known Activations