© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12848
    Prev
    Next
    INDEX
    Explanations

    words that indicate associations between things

    oai_token-act-pair · gemini-2.0-flash

    scientific research

    np_max-act-logits · 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
     connected
    -1.41
     connection
    -1.41
     connections
    -1.40
     Connection
    -1.38
     connecting
    -1.33
     Connected
    -1.31
     connect
    -1.30
     Connections
    -1.30
     CONNECT
    -1.27
     Connecting
    -1.23
    POSITIVE LOGITS
     jueces
    0.43
     aluno
    0.36
    ▾
    0.34
    ubert
    0.34
     pokra
    0.33
     senjata
    0.33
     mortos
    0.33
    рги
    0.32
     Parker
    0.32
    EObject
    0.32
    Activations Density 2.038%

    No Known Activations