© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12398
    Prev
    Next
    INDEX
    Explanations

    the word "coffee" and other retail-related words.

    oai_token-act-pair · gemini-2.0-flash

    Coffee and wine

    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
     natale
    -0.49
    Eloquent
    -0.45
     erinnern
    -0.44
     suaminya
    -0.44
    Xna
    -0.43
    adon
    -0.43
    SHAW
    -0.43
    וויק
    -0.42
    volmente
    -0.41
    used
    -0.41
    POSITIVE LOGITS
    tagHelperRunner
    0.85
    SharedCtor
    0.78
    richTextPanel
    0.60
    TagHelper
    0.57
    ẵng
    0.55
    ########.
    0.55
    FXMLLoader
    0.55
     dataGridView
    0.52
    RRect
    0.52
     holder
    0.51
    Activations Density 1.043%

    No Known Activations