© 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. 3710
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to business, insurance, marketing and legal domains

    oai_token-act-pair · gemini-2.0-flash

    company

    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
    ViewImports
    -0.52
     pygame
    -0.51
    باح
    -0.48
    netbeans
    -0.46
    gridy
    -0.45
    SupportActionBar
    -0.44
    rž
    -0.44
    AsyncResult
    -0.42
     Heim
    -0.41
    vyn
    -0.41
    POSITIVE LOGITS
     company
    2.27
    company
    1.99
     companies
    1.84
    Company
    1.83
     Company
    1.83
     COMPANY
    1.73
    Companies
    1.65
     Companies
    1.63
    companies
    1.62
    COMPANY
    1.62
    Activations Density 2.370%

    No Known Activations