© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12915
    Prev
    Next
    INDEX
    Explanations

    mathematical notation

    oai_token-act-pair · gemini-2.0-flash

    mathematical notations and symbols

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

    mathcal

    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
    ComponentModel
    -0.48
    stanti
    -0.46
     /*
    -0.42
    sid
    -0.41
    ylus
    -0.41
     turbidity
    -0.41
    hor
    -0.40
     conto
    -0.40
    .
    -0.40
     voorbij
    -0.40
    POSITIVE LOGITS
    abestanden
    0.94
    enumii
    0.94
    parsedMessage
    0.85
    QMetaType
    0.84
    Хьажоргаш
    0.80
     doInBackground
    0.76
     فريبيس
    0.75
    Gambas
    0.71
    mobileqq
    0.70
    ftagPool
    0.69
    Activations Density 2.487%

    No Known Activations