© 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. 6841
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to legal and financial documents

    oai_token-act-pair · gemini-2.0-flash

    words ending in "-ly"

    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
    ChildScrollView
    -0.81
     Efq
    -0.79
    arraycopy
    -0.73
     ویکی‌پدی
    -0.73
    GeneratedCode
    -0.71
    StoryboardSegue
    -0.70
     CreateTagHelper
    -0.69
    XmlAccessType
    -0.69
     autorytatywna
    -0.66
    ρίες
    -0.65
    POSITIVE LOGITS
     heavily
    1.32
     deeply
    1.16
     strongly
    1.16
     widely
    1.16
     fully
    1.09
     badly
    1.06
     tightly
    1.04
     closely
    1.03
     hotly
    0.96
    strongly
    0.96
    Activations Density 14.498%

    No Known Activations