© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10190
    Prev
    Next
    INDEX
    Explanations

    numerical probability calculations and academic citations.

    oai_token-act-pair · gemini-2.0-flash

    Non-English terms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     scolaires
    -0.93
     religieuses
    -0.91
     asiatique
    -0.90
     chinoise
    -0.90
     Dumnezeu
    -0.90
     culturelles
    -0.89
     chrétien
    -0.89
     présidenti
    -0.88
     nationaux
    -0.86
     médié
    -0.86
    POSITIVE LOGITS
    parsedMessage
    0.63
    MessageTagHelper
    0.58
    /*
    0.56
     الحره
    0.53
     apellidos
    0.49
     intptr
    0.49
     становника
    0.48
     متعلقه
    0.47
     BorderRadius
    0.47
    DoubleQuotes
    0.46
    Activations Density 72.178%

    No Known Activations