© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12566
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to friendship, attraction, love, and relationships

    oai_token-act-pair · gemini-2.0-flash

    romance and relationships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    Dating
    -0.63
     dating
    -0.63
     Dating
    -0.62
    dating
    -0.61
     breakup
    -0.60
     romances
    -0.56
     kisses
    -0.54
     Lovers
    -0.50
    TargetException
    -0.50
    恋
    -0.50
    POSITIVE LOGITS
    localctx
    0.59
    resizingMask
    0.57
    XDECREF
    0.55
    KURZBESCHREIBUNG
    0.55
    yszer
    0.52
    աստ
    0.52
     Normdatei
    0.51
     connexes
    0.51
     Suivez
    0.50
    ful
    0.50
    Activations Density 15.417%

    No Known Activations