© 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. 10078
    Prev
    Next
    INDEX
    Explanations

    technical academic jargon and terminology.

    oai_token-act-pair · gemini-2.0-flash

    Punctuation

    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
    Geplaatst
    -1.06
    TagMode
    -1.06
    
    -1.06
    Personendaten
    -1.05
     nakalista
    -1.01
    MigrationBuilder
    -0.97
     EconPapers
    -0.97
    Personensuche
    -0.96
     ویکی‌پدی
    -0.94
    Tembelea
    -0.94
    POSITIVE LOGITS
    ,
    0.74
    .
    0.63
     in
    0.62
    :
    0.53
     to
    0.52
     is
    0.51
     for
    0.50
     from
    0.50
    !
    0.48
     (
    0.47
    Activations Density 51.648%

    No Known Activations