© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12719
    Prev
    Next
    INDEX
    Explanations

    words that describe a romantic relationship

    oai_token-act-pair · gemini-2.0-flash

    relationships/friendships

    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
    تقاوى
    -0.53
     Sabha
    -0.48
     >=",
    -0.47
     NSCoder
    -0.46
    ंदीखरीदारी
    -0.46
     Allociné
    -0.45
     branded
    -0.45
    ulence
    -0.44
    ρίς
    -0.44
     CharSequence
    -0.43
    POSITIVE LOGITS
     boyfriend
    0.96
     friend
    0.95
    friend
    0.94
     roommate
    0.92
    Friend
    0.89
     boyfriends
    0.88
     roommates
    0.87
    boyfriend
    0.84
     Friend
    0.83
     neighbours
    0.83
    Activations Density 2.003%

    No Known Activations