© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14169
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to leadership and organizations

    oai_token-act-pair · gemini-2.0-flash

    positions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     capacity
    -0.98
    capacity
    -0.81
     Capacity
    -0.80
    Capacity
    -0.80
     CAPACITY
    -0.69
     capacité
    -0.62
    kháu
    -0.62
     role
    -0.62
     capacidade
    -0.62
     capacidad
    -0.60
    POSITIVE LOGITS
     places
    0.77
     positions
    0.71
     posts
    0.71
     seats
    0.66
    places
    0.65
     Places
    0.64
     spots
    0.64
     PLACES
    0.63
    پیوند
    0.63
     careers
    0.62
    Activations Density 1.329%

    No Known Activations