© 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. 9771
    Prev
    Next
    INDEX
    Explanations

    political and governmental terms, especially in the context of conflict and power.

    oai_token-act-pair · gemini-2.0-flash

    political power, war, regimes

    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
    
    -0.68
    PropertyChanging
    -0.66
     &___
    -0.60
     useRouter
    -0.60
    SequentialGroup
    -0.60
    WriteBarrier
    -0.59
     springfox
    -0.57
     useNavigate
    -0.56
     TextFormField
    -0.56
    twimg
    -0.55
    POSITIVE LOGITS
    chauung
    0.54
    !")
    0.54
    chism
    0.51
    épend
    0.48
    .")
    0.48
    ernalia
    0.46
    ();
    0.46
     Rakyat
    0.46
    =<?
    0.45
    Aholisi
    0.44
    Activations Density 18.400%

    No Known Activations