© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2050
    Prev
    Next
    INDEX
    Explanations

    terminology related to weather modification and data analysis

    oai_token-act-pair · gemini-2.0-flash

    cloud seeding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    queryInterface
    -0.63
     незавершена
    -0.63
    Explicación
    -0.56
    PhysRevLett
    -0.56
    enné
    -0.51
    httphttps
    -0.50
    shund
    -0.50
    뀔
    -0.50
    Kjelder
    -0.50
    aband
    -0.50
    POSITIVE LOGITS
    VSS
    0.50
     ESTR
    0.48
    TemporalType
    0.47
    CellStyle
    0.47
     lepid
    0.46
     viață
    0.45
    rxjs
    0.45
     întâ
    0.45
    Datuak
    0.45
     चीज़ों
    0.44
    Activations Density 34.617%

    No Known Activations