© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9859
    Prev
    Next
    INDEX
    Explanations

    instances of "we are" or "we're"

    oai_token-act-pair · gemini-2.0-flash

    Capitalized proper nouns

    np_token-act-pair-logits · gpt-4o-mini

    are

    np_max-act-logits · gemini-2.0-flash
    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
     our
    -0.54
    our
    -0.51
     vårt
    -0.46
    kuuta
    -0.45
     наш
    -0.44
     /\.
    -0.42
     наше
    -0.41
     bestehen
    -0.39
     ملف
    -0.39
     nuestro
    -0.38
    POSITIVE LOGITS
    tanleria
    0.83
    IUrlHelper
    0.82
    RegressionTest
    0.80
    Their
    0.79
     CreateTagHelper
    0.74
    InputBorder
    0.73
    principalTable
    0.72
     geologists
    0.68
     Their
    0.66
     Cæsar
    0.66
    Activations Density 1.939%

    No Known Activations