© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4714
    Prev
    Next
    INDEX
    Explanations

    instances where someone is falling in love or feeling emotions

    oai_token-act-pair · gemini-2.0-flash

    fall

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     fall
    -2.73
     fallen
    -2.61
     falling
    -2.58
     falls
    -2.55
     fell
    -2.53
    fall
    -2.52
    Fall
    -2.50
     Fall
    -2.45
     FALL
    -2.44
     Falling
    -2.44
    POSITIVE LOGITS
     vastaan
    0.51
     Chiron
    0.47
    uestamente
    0.43
    csol
    0.40
     Mön
    0.40
     gladiator
    0.39
     magnification
    0.39
    lysninger
    0.39
     käyttö
    0.38
     Bestimm
    0.38
    Activations Density 1.824%

    No Known Activations