© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7476
    Prev
    Next
    INDEX
    Explanations

    instances of connector words such as "that", "and", "but", "like", etc

    oai_token-act-pair · gemini-2.0-flash

    Negative arguments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
     ModelExpression
    -1.02
     autorytatywna
    -0.90
     AssemblyTitle
    -0.86
     للاسماء
    -0.84
     resourceCulture
    -0.77
    AutoField
    -0.76
     jScrollPane
    -0.75
     الحره
    -0.74
     Administrativna
    -0.71
     betweenstory
    -0.71
    POSITIVE LOGITS
     while
    0.45
     most
    0.43
     volunt
    0.41
     Zwie
    0.40
     continuous
    0.40
    Crossref
    0.40
     being
    0.39
     hands
    0.39
    most
    0.38
    χαν
    0.38
    Activations Density 2.124%

    No Known Activations