© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6490
    Prev
    Next
    INDEX
    Explanations

    words related to energy, recycling, small machines, and scientific equipment

    oai_token-act-pair · gemini-2.0-flash

    Small systems

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    IntoConstraints
    -0.70
    SharedCtor
    -0.70
     defStyle
    -0.70
    存于互联网档案馆
    -0.69
     للمعارف
    -0.65
    rungsseite
    -0.64
    новниш
    -0.64
     zelve
    -0.62
     ?>>
    -0.60
    BibitemShut
    -0.60
    POSITIVE LOGITS
     system
    0.57
    system
    0.53
     min
    0.50
    usercontent
    0.49
     mini
    0.49
     System
    0.47
    __':
    0.47
     sistema
    0.46
     мини
    0.44
     systems
    0.42
    Activations Density 2.314%

    No Known Activations