© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5276
    Prev
    Next
    INDEX
    Explanations

    mentions of relationships, especially where they are challenged.

    oai_token-act-pair · gemini-2.0-flash

    phrases related to couples and families

    np_token-act-pair-logits · gpt-4o-mini

    couple

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     user
    -0.68
    user
    -0.65
     User
    -0.55
    User
    -0.53
     USER
    -0.51
    makeText
    -0.51
     समीक्षक
    -0.49
    AndroidJUnit
    -0.45
     utilisateur
    -0.45
     usuário
    -0.44
    POSITIVE LOGITS
     couple
    1.62
     couples
    1.59
    couple
    1.45
     Couple
    1.31
     families
    1.29
    couples
    1.27
    Couple
    1.27
     Couples
    1.26
    families
    1.13
    Coup
    1.13
    Activations Density 3.986%

    No Known Activations