© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4886
    Prev
    Next
    INDEX
    Explanations

    the prefix "nong" or names starting with the letter "G."

    oai_token-act-pair · gemini-2.0-flash

    non-credibility indicators

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

    Code and technical language

    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
    PreferredItem
    -0.49
     ویکی‌پدی
    -0.46
     typ
    -0.45
     *)__
    -0.43
     cry
    -0.43
     MonoBehaviour
    -0.42
    tagHelperRunner
    -0.41
     PLWABN
    -0.40
     mus
    -0.40
     utafiti
    -0.40
    POSITIVE LOGITS
     AssemblyVersion
    0.71
     disponibilités
    0.71
    RegistryLite
    0.67
    存于互联网档案馆
    0.67
     endregion
    0.66
    MemoryWarning
    0.64
    nextProps
    0.62
    Välislingid
    0.61
    mability
    0.60
    WithMany
    0.60
    Activations Density 0.519%

    No Known Activations