© 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
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 210
    Prev
    Next
    INDEX
    Explanations

    words and phrases involved in love/medical procedures/electrical signals

    oai_token-act-pair · gemini-2.0-flash

    Couples/pairs and medical devices

    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
     duo
    -0.89
     duos
    -0.78
    pair
    -0.75
     beide
    -0.73
     Couple
    -0.73
     pair
    -0.73
     duet
    -0.73
    Both
    -0.72
     pairing
    -0.69
     entrambi
    -0.69
    POSITIVE LOGITS
     everyone
    0.70
     allemaal
    0.67
    everyone
    0.60
     iedereen
    0.60
     Everyone
    0.60
    Assemblée
    0.56
    Everyone
    0.55
     cast
    0.54
    みんなで
    0.53
     multiple
    0.52
    Activations Density 2.770%

    No Known Activations