© 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. 8222
    Prev
    Next
    INDEX
    Explanations

    statistical and reporting phrases involving company names

    oai_token-act-pair · gemini-2.0-flash

    technical or specialized terminology

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

    surveys and statistics

    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
    канчи
    -0.50
    contentLoaded
    -0.50
    ագրություններ
    -0.49
     externi
    -0.48
     Audiodateien
    -0.46
    BASS
    -0.45
     otomatig
    -0.44
     ?>>
    -0.43
     invokingState
    -0.43
     south
    -0.42
    POSITIVE LOGITS
    regierung
    0.62
    RegressionTest
    0.59
     oliveira
    0.58
     tutkim
    0.57
     makeStyles
    0.57
    Према
    0.56
     BorderRadius
    0.56
     lende
    0.55
    følgelig
    0.55
    EventLoop
    0.54
    Activations Density 2.120%

    No Known Activations