© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15378
    Prev
    Next
    INDEX
    Explanations

    words/names associated with political people or organizations

    oai_token-act-pair · gemini-2.0-flash

    international relations and news

    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
    Personensuche
    -0.75
     StatefulWidget
    -0.74
    ANTLR
    -0.70
    GOTREF
    -0.66
    createCanvas
    -0.64
    ImageContext
    -0.62
    UnusedPrivate
    -0.61
     विश्वसनीयता
    -0.60
     NgModule
    -0.60
    AddTagHelper
    -0.60
    POSITIVE LOGITS
     présidenti
    0.63
     phénomènes
    0.59
     légiti
    0.57
     oublier
    0.57
     réguli
    0.56
     démission
    0.56
     sauvages
    0.56
     supérieurs
    0.55
     définiti
    0.54
    帖最后由
    0.54
    Activations Density 3.133%

    No Known Activations