© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11891
    Prev
    Next
    INDEX
    Explanations

    instances of the words "could", "they", "you", "she", "so", "who", on the periphery of descriptive statements

    oai_token-act-pair · gemini-2.0-flash

    could

    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
    contentLoaded
    -0.88
    الإنجليزية
    -0.77
     defaultstate
    -0.77
    posedge
    -0.73
    BufferException
    -0.73
    :✨
    -0.68
    ,‎
    -0.65
    IndentedString
    -0.65
    styleType
    -0.65
     دیکھیے
    -0.65
    POSITIVE LOGITS
     could
    1.95
     Could
    1.58
    Could
    1.55
    could
    1.54
     COULD
    1.17
     könnten
    0.93
     могли
    0.85
     podría
    0.85
     possible
    0.83
     мог
    0.83
    Activations Density 4.683%

    No Known Activations