© 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. 10784
    Prev
    Next
    INDEX
    Explanations

    first person pronouns used with auxiliary verbs or the word "than"

    oai_token-act-pair · gemini-2.0-flash

    surprise

    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
     initComponents
    -0.92
     AssemblyCulture
    -0.71
    IUrlHelper
    -0.69
     hObject
    -0.68
    RegistryLite
    -0.68
     Мексичка
    -0.66
     AssemblyTitle
    -0.66
    SequentialGroup
    -0.65
     EconPapers
    -0.65
    PreExecute
    -0.63
    POSITIVE LOGITS
    ̵
    0.51
     federal
    0.48
    ).\
    0.47
     want
    0.47
     di
    0.47
     Dür
    0.45
    Tembelea
    0.45
    maxcdn
    0.44
     plan
    0.44
     Menon
    0.44
    Activations Density 3.583%

    No Known Activations