© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14290
    Prev
    Next
    INDEX
    Explanations

    words and phrases about someone holding a job, playing a sport, and the passage of time

    oai_token-act-pair · gemini-2.0-flash

    with

    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
    AddTagHelper
    -1.05
     nakalista
    -1.03
    Personensuche
    -0.96
    StructEnd
    -0.90
    MemoryWarning
    -0.88
     ModelExpression
    -0.87
     Audiodateien
    -0.85
    rawDesc
    -0.85
    EndInit
    -0.82
    تقاوى
    -0.82
    POSITIVE LOGITS
     with
    2.72
    with
    2.00
     avec
    1.98
     dengan
    1.80
     WITH
    1.73
     With
    1.70
    With
    1.70
     với
    1.64
    avec
    1.37
     עם
    1.30
    Activations Density 1.660%

    No Known Activations