© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10851
    Prev
    Next
    INDEX
    Explanations

    words in various languages related to website menus, food science, religious categories, pneumonia, medical procedures, and code repositories.

    oai_token-act-pair · gemini-2.0-flash

    Prefixes and multiple languages

    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
    saturday
    -0.55
    slavery
    -0.55
    wijze
    -0.52
     %>%
    -0.49
    
    -0.48
    vriende
    -0.48
     a
    -0.47
    Weblinks
    -0.46
    uncertainty
    -0.46
    któ
    -0.46
    POSITIVE LOGITS
    IsContent
    0.84
    OGND
    0.75
     Monfieur
    0.75
    onOptions
    0.75
    piram
    0.73
     nakalista
    0.72
     unſ
    0.68
     doubtnut
    0.68
     himo
    0.68
     ſtate
    0.67
    Activations Density 0.347%

    No Known Activations