© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4127
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to couples and marriage and the royal family

    oai_token-act-pair · gemini-2.0-flash

    couples/pairs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Männer
    -1.41
     Männern
    -1.34
     hommes
    -1.31
     masculina
    -1.26
     masculine
    -1.23
     masculinity
    -1.21
     boys
    -1.18
     men
    -1.18
     male
    -1.17
     males
    -1.17
    POSITIVE LOGITS
    恋人
    0.50
    ppet
    0.46
    TagHelper
    0.46
     dual
    0.46
     multi
    0.45
     Kokos
    0.45
    ppets
    0.45
    нодоро
    0.44
    RTDA
    0.44
     Knock
    0.44
    Activations Density 0.568%

    No Known Activations