© 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. 4670
    Prev
    Next
    INDEX
    Explanations

    code snippets with syntax relating to objects, deletion, and type errors

    oai_token-act-pair · gemini-2.0-flash

    occurrences of "property"

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

    property/properties

    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
    kmäler
    -0.56
    AccessorTable
    -0.55
     cherchés
    -0.54
    تقاوى
    -0.53
    iseta
    -0.50
    edale
    -0.49
    큼
    -0.48
    PreExecute
    -0.47
    CDCl
    -0.47
    RetentionPolicy
    -0.47
    POSITIVE LOGITS
     property
    1.50
     properties
    1.45
    Property
    1.34
     Properties
    1.32
    property
    1.30
    properties
    1.27
     Property
    1.26
     PROPERTY
    1.20
    Properties
    1.20
     PROPERTIES
    1.13
    Activations Density 4.364%

    No Known Activations