© 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. 15205
    Prev
    Next
    INDEX
    Explanations

    words and punctuation related to summaries of historical/political documents, treaties, and negotiations

    oai_token-act-pair · gemini-2.0-flash

    ,

    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
     just
    -0.49
     van
    -0.46
    epik
    -0.44
    etak
    -0.44
    mister
    -0.44
     by
    -0.42
    יד
    -0.42
    ,”
    -0.41
     कर
    -0.41
     rather
    -0.41
    POSITIVE LOGITS
    ReusableCell
    0.86
     tartalomajánló
    0.86
     Cæsar
    0.83
     whoſe
    0.80
     Anſ
    0.76
     Theſe
    0.75
     виправивши
    0.73
     pleaſure
    0.73
    QMetaType
    0.73
    __':
    0.72
    Activations Density 1.223%

    No Known Activations