© 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. 5016
    Prev
    Next
    INDEX
    Explanations

    numbers containing a decimal point, often in lists or tables

    oai_token-act-pair · gemini-2.0-flash

    numbers and punctuation symbols

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

    punctuation

    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
     EconPapers
    -0.94
     <=",
    -0.69
     ujednoznacz
    -0.68
    ьаж
    -0.67
    reactstrap
    -0.66
    ⇑
    -0.66
    homonymie
    -0.65
     חיצוניים
    -0.62
     дописавши
    -0.60
    tagHelperRunner
    -0.60
    POSITIVE LOGITS
    اریخ
    0.56
    saraba
    0.52
    jed
    0.46
    flink
    0.46
    ähne
    0.45
     Wonder
    0.44
    Wallace
    0.43
     Tully
    0.43
    openapi
    0.42
     cé
    0.42
    Activations Density 1.159%

    No Known Activations