© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6758
    Prev
    Next
    INDEX
    Explanations

    phrases about legal proceedings and individuals in an official capacity

    oai_token-act-pair · gemini-2.0-flash

    capacity

    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
     noqa
    -0.68
     ModelExpression
    -0.57
    enedor
    -0.55
    
    -0.54
    ramienta
    -0.54
    tvguidetime
    -0.52
    usiai
    -0.50
     CommonModule
    -0.50
    しく
    -0.48
     sana
    -0.48
    POSITIVE LOGITS
     capacity
    0.88
     capacities
    0.76
    capacity
    0.75
    Capacity
    0.68
     Capacity
    0.67
    capac
    0.59
     capacidad
    0.58
     kapas
    0.57
     <=",
    0.57
     kapasitas
    0.55
    Activations Density 1.902%

    No Known Activations