© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7217
    Prev
    Next
    INDEX
    Explanations

    words or abbreviations referring to people, with a focus on pronouns and mentions of "shear"

    oai_token-act-pair · gemini-2.0-flash

    she

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     esternos
    -0.81
    seamnă
    -0.65
    setVerticalGroup
    -0.65
     betweenstory
    -0.62
     Lumpur
    -0.60
     nahilalakip
    -0.60
     tarko
    -0.59
    selves
    -0.59
    OutputPath
    -0.55
     levis
    -0.54
    POSITIVE LOGITS
    she
    0.54
    ViewImports
    0.54
    gonic
    0.52
     BitmapFactory
    0.48
    enumi
    0.47
    InjectAttribute
    0.47
    __(
    0.47
     She
    0.47
    ParallelGroup
    0.46
     she
    0.46
    Activations Density 0.869%

    No Known Activations