© 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. 6520
    Prev
    Next
    INDEX
    Explanations

    the word "would" and pronouns

    oai_token-act-pair · gemini-2.0-flash

    say "not"

    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
     Won
    -0.61
    !("{}",
    -0.59
    won
    -0.58
     Akira
    -0.57
    Won
    -0.57
     trăm
    -0.56
     resourceCulture
    -0.55
     Мексичка
    -0.54
     Prose
    -0.54
    Lähteet
    -0.54
    POSITIVE LOGITS
     will
    1.40
     would
    1.39
    will
    1.08
    would
    1.02
     Would
    1.02
    Will
    0.99
    Would
    0.99
     Will
    0.97
     akan
    0.94
     sẽ
    0.87
    Activations Density 3.065%

    No Known Activations