© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10022
    Prev
    Next
    INDEX
    Explanations

    code-related text.

    oai_token-act-pair · gemini-2.0-flash

    code and page snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     AssemblyVersion
    -0.68
     AssemblyCompany
    -0.52
    TabLayout
    -0.49
    AnchorTagHelper
    -0.48
    IComponent
    -0.48
    VIAF
    -0.45
    RemoveField
    -0.44
     AssemblyTitle
    -0.44
    InputBorder
    -0.44
     BoxDecoration
    -0.42
    POSITIVE LOGITS
    <bos>
    0.97
     Administrativna
    0.66
    
    0.61
     &___
    0.59
    MigrationBuilder
    0.57
     kaarangay
    0.57
    хьтан
    0.54
    GEBURTSDATUM
    0.54
    endwhile
    0.54
    digd
    0.53
    Activations Density 1.009%

    No Known Activations