© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10812
    Prev
    Next
    INDEX
    Explanations

    African countries and words connecting them

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    AndroidJUnit
    -0.79
    Билгалдахарш
    -0.79
     nargin
    -0.68
    XMLSchema
    -0.64
     XCTest
    -0.63
    multer
    -0.62
     intptr
    -0.61
     Michaelis
    -0.61
    RegistryLite
    -0.60
     Nepal
    -0.58
    POSITIVE LOGITS
    ėja
    0.46
     ET
    0.46
    UnsafeEnabled
    0.45
    ssaint
    0.44
     Jim
    0.44
     ETH
    0.44
     Dire
    0.44
    signol
    0.44
     com
    0.43
     punt
    0.43
    Activations Density 1.316%

    No Known Activations