© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16165
    Prev
    Next
    INDEX
    Explanations

    words related to societal groups, labels for people, and their roles

    oai_token-act-pair · gemini-2.0-flash

    Military, legal and punditry texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    bootstrapcdn
    -0.93
    sider
    -0.74
     major
    -0.71
    Seeder
    -0.70
    KEE
    -0.68
     Major
    -0.68
    masker
    -0.67
    minder
    -0.67
    keeper
    -0.66
    TagHelpers
    -0.64
    POSITIVE LOGITS
    énieurs
    0.62
     enfans
    0.46
     hinweg
    0.46
     comigo
    0.43
    AnimationsModule
    0.42
    ammans
    0.41
    gians
    0.40
    ContentAsync
    0.40
     Humanos
    0.40
     Muses
    0.39
    Activations Density 1.676%

    No Known Activations