© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12998
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to emotions, especially love, feelings, and mental states.

    oai_token-act-pair · gemini-2.0-flash

    love

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    DockStyle
    -0.59
     Pristupljeno
    -0.58
    providedIn
    -0.58
    aperto
    -0.54
    Fordítás
    -0.54
     ProtoMessage
    -0.54
     الرياضيه
    -0.53
    WaitGroup
    -0.53
     Pingback
    -0.52
    évaluateur
    -0.51
    POSITIVE LOGITS
     infatu
    0.75
     love
    0.62
     affection
    0.56
     romance
    0.54
    love
    0.50
    zeczy
    0.49
     romances
    0.49
     enchantment
    0.49
     romantic
    0.48
    MOD
    0.47
    Activations Density 1.641%

    No Known Activations