© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9873
    Prev
    Next
    INDEX
    Explanations

    language discussing political parties and political positions

    oai_token-act-pair · gemini-2.0-flash

    politics

    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
    WebVitals
    -0.59
    httphttps
    -0.58
    aarrggbb
    -0.55
    DrawerToggle
    -0.53
     مشين
    -0.51
     UIFont
    -0.50
     Humb
    -0.49
     invokingState
    -0.49
    
    -0.47
    PRNewswire
    -0.47
    POSITIVE LOGITS
     AssemblyTitle
    0.68
     isolato
    0.63
    banking
    0.60
     Савезне
    0.60
     deltaTime
    0.56
     aislado
    0.55
     Ejecutivo
    0.55
     banking
    0.55
     térmico
    0.55
     aconteceu
    0.54
    Activations Density 2.103%

    No Known Activations