© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3293
    Prev
    Next
    INDEX
    Explanations

    information related to law enforcement arrests, searches, and charges.

    oai_token-act-pair · gemini-2.0-flash

    crime and legal matters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    writeFieldEnd
    -0.57
     AssemblyVersion
    -0.54
     occhiali
    -0.52
    AccessorTable
    -0.51
     Schwal
    -0.50
     Choice
    -0.49
     Monsters
    -0.48
    openConnection
    -0.48
    codegen
    -0.47
     pulumi
    -0.47
    POSITIVE LOGITS
    ViewImports
    0.52
    GEBURTS
    0.51
     CiNii
    0.50
    zola
    0.49
    AddHtmlAttribute
    0.49
    eqn
    0.47
    RegressionTest
    0.47
     urat
    0.45
    ABET
    0.45
    HttpFoundation
    0.45
    Activations Density 1.514%

    No Known Activations