© 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. 9707
    Prev
    Next
    INDEX
    Explanations

    numbers and letters in legal or mathematical contexts

    oai_token-act-pair · gemini-2.0-flash

    words related to legal terms or jargon

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

    Uncommon words

    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
    beitet
    -0.45
    zk
    -0.44
     semi
    -0.43
    ornal
    -0.43
     sem
    -0.43
    IsContent
    -0.43
     anti
    -0.42
     kur
    -0.42
     zak
    -0.41
    <eos>
    -0.40
    POSITIVE LOGITS
     purpoſe
    0.72
    Sucesor
    0.71
    queryInterface
    0.71
     houſe
    0.70
     كومونز
    0.68
     ſame
    0.68
     kasarigan
    0.68
     وتسجيلات
    0.68
    WireFormatLite
    0.66
     Wikimedijinoj
    0.66
    Activations Density 2.831%

    No Known Activations