© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12496
    Prev
    Next
    INDEX
    Explanations

    code snippets including specific C# syntax and terms like overload, anonymous methods, and function expressions

    oai_token-act-pair · gemini-2.0-flash

    technical terms related to programming and software

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

    code methods and functions

    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
    Property
    -0.88
     property
    -0.86
     properties
    -0.85
     Properties
    -0.83
     Property
    -0.81
    properties
    -0.81
    Properties
    -0.77
    property
    -0.71
     fields
    -0.70
     PROPERTY
    -0.68
    POSITIVE LOGITS
    lwjgl
    0.62
    bleshooting
    0.60
    RetentionPolicy
    0.57
    Kjelder
    0.57
    цездатний
    0.57
    iseta
    0.55
     BODY
    0.54
    DialogInterface
    0.51
    ék
    0.50
     bodies
    0.49
    Activations Density 3.173%

    No Known Activations