© 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. 2347
    Prev
    Next
    INDEX
    Explanations

    geopolitical terms followed by named individuals, regions, and some words related to music

    oai_token-act-pair · gemini-2.0-flash

    Middle East, West, East

    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
     West
    -2.64
     Western
    -2.61
    West
    -2.59
     western
    -2.58
     west
    -2.56
     WEST
    -2.55
    Western
    -2.55
    west
    -2.41
    WEST
    -2.38
     WESTERN
    -2.36
    POSITIVE LOGITS
    bootstrapcdn
    0.53
    новниш
    0.48
    DBNull
    0.48
    MetaObject
    0.47
     Löwen
    0.44
    Linki
    0.44
     gyhoeddwyd
    0.42
    Cyfeiriadau
    0.42
     giraffe
    0.41
     Darum
    0.41
    Activations Density 1.855%

    No Known Activations