© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9331
    Prev
    Next
    INDEX
    Explanations

    mentions of love and relationships

    oai_token-act-pair · gemini-2.0-flash

    love or strong feelings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Love
    -2.66
     love
    -2.61
    Love
    -2.55
     LOVE
    -2.52
    love
    -2.47
    LOVE
    -2.41
     loved
    -2.36
     loving
    -2.30
     loves
    -2.17
    loved
    -2.09
    POSITIVE LOGITS
     mergeFrom
    0.60
     preprint
    0.47
    BufferException
    0.46
    المكان
    0.45
     Schell
    0.43
    ору
    0.43
     MPP
    0.43
     inal
    0.43
    клопе
    0.42
     Bundy
    0.42
    Activations Density 1.389%

    No Known Activations