© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11581
    Prev
    Next
    INDEX
    Explanations

    various elements of Swift, Protobuf, and possibly other C-like code including get/set, case statements, and some special characters

    oai_token-act-pair · gemini-2.0-flash

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    </strong>
    -0.62
    </em>
    -0.52
     eset
    -0.49
      
    -0.48
    wicz
    -0.47
     V
    -0.47
    רית
    -0.47
    <strong>
    -0.46
    ↵
    -0.45
     Steine
    -0.45
    POSITIVE LOGITS
    parsedMessage
    1.25
    AddTagHelper
    1.17
    DockStyle
    1.06
    RenderAtEndOf
    1.05
    SourceChecksum
    1.03
     مشين
    0.97
    ValueStyle
    0.97
     AssemblyCompany
    0.95
    MigrationBuilder
    0.95
     <<<<<<<<<<<<<<
    0.94
    Activations Density 1.093%

    No Known Activations