© 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. 5441
    Prev
    Next
    INDEX
    Explanations

    author names in academic citations

    oai_token-act-pair · gemini-2.0-flash

    non-English text or unusual symbols

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

    Citations

    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
     umani
    -0.41
     porc
    -0.40
     dokumenta
    -0.39
     membrana
    -0.39
     bipartisan
    -0.38
     cuivre
    -0.38
     biografi
    -0.38
     libertà
    -0.38
     bone
    -0.37
    事態
    -0.37
    POSITIVE LOGITS
    rungsseite
    0.74
     kasarigan
    0.71
    >--}}
    0.70
     '\\;'
    0.70
     lenker
    0.70
     محفوظة
    0.69
    setViewportView
    0.69
    ibrill
    0.69
    Erreferentziak
    0.67
     AttributeSet
    0.66
    Activations Density 0.879%

    No Known Activations