© 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. 13697
    Prev
    Next
    INDEX
    Explanations

    words related to historical and political conflict, particularly treaties, persecution, and governmental actions.

    oai_token-act-pair · gemini-2.0-flash

    historical/legal documents

    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
     StyleSheet
    -0.70
    ImageContext
    -0.63
    abestanden
    -0.62
    StoryboardSegue
    -0.61
    AndEndTag
    -0.60
     الرياضيه
    -0.59
    Expedia
    -0.56
    fjspx
    -0.56
    findpost
    -0.56
    tagHelperRunner
    -0.55
    POSITIVE LOGITS
    WireFormatLite
    0.57
    ModelAdmin
    0.52
    Check
    0.50
     EEU
    0.49
     préf
    0.49
     tend
    0.48
     checked
    0.48
     dégust
    0.48
     Susanna
    0.47
    check
    0.47
    Activations Density 3.827%

    No Known Activations