© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13447
    Prev
    Next
    INDEX
    Explanations

    mentions of people, locations and dates, especially as related to family history or biography

    oai_token-act-pair · gemini-2.0-flash

    Legal / names

    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
     "..\..\
    -0.75
    :✨
    -0.73
     '\\;'
    -0.72
    TypedDataSet
    -0.71
     "..\..\..\
    -0.71
    otras
    -0.64
    modelBuilder
    -0.61
    ✭✭
    -0.61
     allAfrica
    -0.60
    <bos>
    -0.60
    POSITIVE LOGITS
    Autoritní
    0.49
    tų
    0.38
     of
    0.36
     henkil
    0.36
     sanitaires
    0.34
    verlag
    0.34
    oarece
    0.32
    方で
    0.32
    ;">
    0.32
     وتسجيلات
    0.32
    Activations Density 1.575%

    No Known Activations