© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3740
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to commercial and population growth

    oai_token-act-pair · gemini-2.0-flash

    terms related to business growth and revenue

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    IntoConstraints
    -0.62
    Expect
    -0.59
     will
    -0.56
    
    -0.55
    Will
    -0.50
     Expect
    -0.49
    ModelForm
    -0.49
     rowspan
    -0.48
    willReturn
    -0.48
     Absicht
    -0.48
    POSITIVE LOGITS
    ThroughAttribute
    0.89
     devons
    0.65
     للمعارف
    0.63
     can
    0.61
     galima
    0.61
    Diwedd
    0.60
     كومونز
    0.59
     oprot
    0.59
     pouvez
    0.59
     posso
    0.59
    Activations Density 1.073%

    No Known Activations