© 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. 13200
    Prev
    Next
    INDEX
    Explanations

    names in the context of organizational staff

    oai_token-act-pair · gemini-2.0-flash

    leaving

    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
    cosis
    -0.50
     Öl
    -0.48
     thiệu
    -0.48
    nischer
    -0.45
    ToInt
    -0.45
    DataObject
    -0.44
    temos
    -0.43
    Bronnen
    -0.43
    nischen
    -0.42
    ohar
    -0.42
    POSITIVE LOGITS
     departure
    1.45
     leaving
    1.41
    Leaving
    1.41
     Leaving
    1.36
    leaving
    1.27
     leave
    1.24
     quitté
    1.24
     Departure
    1.20
    leave
    1.20
     departing
    1.20
    Activations Density 1.567%

    No Known Activations