© 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. 3050
    Prev
    Next
    INDEX
    Explanations

    mentions of scientific or mathematical data and figures

    oai_token-act-pair · gemini-2.0-flash

    non-English words and symbols

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

    Technical exclusion/comparison

    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
     uitz
    -0.48
    rather
    -0.47
    isEqualTo
    -0.47
    Z
    -0.47
    MIDDLEWARE
    -0.46
    than
    -0.46
    Rather
    -0.46
     adalah
    -0.45
     rather
    -0.45
     Z
    -0.45
    POSITIVE LOGITS
     não
    0.96
    expandindo
    0.95
    χι
    0.87
     <>",
    0.86
     didn
    0.83
     không
    0.79
    Não
    0.77
     don
    0.77
     Não
    0.77
    UIControlState
    0.74
    Activations Density 1.987%

    No Known Activations