© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10986
    Prev
    Next
    INDEX
    Explanations

    the word "guys" or "guy"

    oai_token-act-pair · gemini-2.0-flash

    guys

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     guy
    -2.20
     guys
    -1.90
    guy
    -1.67
     GUY
    -1.66
    guys
    -1.60
    Guys
    -1.58
     Guys
    -1.52
    Guy
    -1.45
     Guy
    -1.44
     GUYS
    -1.42
    POSITIVE LOGITS
    #+#
    0.57
    ClientSize
    0.55
    ReusableCell
    0.53
    setVerticalGroup
    0.49
     numberOfRows
    0.47
     Taktlose
    0.45
    acrylate
    0.45
    AnchorStyles
    0.45
    maakt
    0.44
    namentales
    0.43
    Activations Density 0.965%

    No Known Activations