© 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. 2978
    Prev
    Next
    INDEX
    Explanations

    text in languages other than English (mixed with code)

    oai_token-act-pair · gemini-2.0-flash

    phrases indicating source or authorship

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

    "by" in different languages

    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
     bílá
    -0.47
    もしれません
    -0.47
    abilirsiniz
    -0.47
    hdessä
    -0.47
     města
    -0.45
     kanssa
    -0.44
     súčas
    -0.43
     Romains
    -0.43
     černá
    -0.42
     amarilla
    -0.41
    POSITIVE LOGITS
     by
    2.25
     oleh
    1.83
     By
    1.62
    by
    1.60
    By
    1.48
     przez
    1.48
     bởi
    1.48
     BY
    1.38
     pelos
    1.27
     ידי
    1.25
    Activations Density 0.421%

    No Known Activations