© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13817
    Prev
    Next
    INDEX
    Explanations

    code snippets with references to variables and strings.

    oai_token-act-pair · gemini-2.0-flash

    programming and database operations

    np_token-act-pair-logits · gpt-4o-mini

    code context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    SequentialGroup
    -0.80
     BoxDecoration
    -0.77
    RRect
    -0.73
    TagMode
    -0.68
    AddTagHelper
    -0.67
     AssemblyVersion
    -0.62
     EconPapers
    -0.60
    ISupport
    -0.57
    FontOfSize
    -0.57
    </thead>
    -0.57
    POSITIVE LOGITS
     Italijanski
    0.58
     Италијани
    0.44
     reach
    0.43
     SEDS
    0.43
     ModelExpression
    0.42
     amp
    0.41
     def
    0.41
    />";
    0.39
     .
    0.39
     go
    0.37
    Activations Density 3.083%

    No Known Activations