© 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. 4140
    Prev
    Next
    INDEX
    Explanations

    scientific research papers

    oai_token-act-pair · gemini-2.0-flash

    technical or scientific terms

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

    Reconstruction methods

    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
     ISNI
    -0.65
     autorytatywna
    -0.62
    QMetaType
    -0.53
    contentLoaded
    -0.47
     propOrder
    -0.47
    fromUtf
    -0.46
    сист
    -0.46
     sale
    -0.44
    PyExc
    -0.44
     Terms
    -0.44
    POSITIVE LOGITS
    glEnd
    0.69
    parsedMessage
    0.61
    ruptedException
    0.61
    richTextPanel
    0.60
    GEBURTS
    0.60
    pencer
    0.57
    οντας
    0.56
    chymal
    0.55
    ernalia
    0.55
    berdayakan
    0.54
    Activations Density 5.813%

    No Known Activations