© 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. 15020
    Prev
    Next
    INDEX
    Explanations

    document formatting markers like paragraph and figure labels

    oai_token-act-pair · gemini-2.0-flash

    non-English characters and symbols

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

    Legal/technical references

    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
    \{\\
    -0.82
     pinulongan
    -0.66
    Demografia
    -0.65
    出版年
    -0.61
    MessageTagHelper
    -0.59
    alyptus
    -0.59
    ゴリー
    -0.57
    esgue
    -0.57
    apunov
    -0.57
    rungsseite
    -0.56
    POSITIVE LOGITS
    達
    0.75
    ów
    0.63
    lar
    0.63
    ů
    0.62
    ら
    0.62
    []
    0.62
    々
    0.60
    []>
    0.60
    들
    0.59
    ҳо
    0.58
    Activations Density 0.430%

    No Known Activations