© 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. 12519
    Prev
    Next
    INDEX
    Explanations

    legal and regulatory text

    oai_token-act-pair · gemini-2.0-flash

    foreign language tokens

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

    computer code and licenses

    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
    ’
    -0.56
     &
    -0.55
    es
    -0.54
    <bos>
    -0.53
    re
    -0.52
    1
    -0.51
    ,
    -0.51
    t
    -0.50
    0
    -0.49
    ↵
    -0.48
    POSITIVE LOGITS
     كومونز
    1.17
     يتيمه
    1.16
     <=",
    1.13
    帖最后由
    1.11
     مشين
    1.09
     تانيه
    1.07
     ویکی‌پدیای
    1.07
     Audiodateien
    1.07
     विश्वसनीयता
    1.07
     >=",
    1.06
    Activations Density 4.887%

    No Known Activations