© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9636
    Prev
    Next
    INDEX
    Explanations

    mentions of US states, particularly in the South, along with mentions of violence

    oai_token-act-pair · gemini-2.0-flash

    Carolina mentions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    èdia
    -0.56
     South
    -0.49
     bet
    -0.46
     Meridian
    -0.46
    #+#
    -0.45
     Seoul
    -0.45
    orological
    -0.43
    South
    -0.43
    >);
    -0.43
    PageContext
    -0.43
    POSITIVE LOGITS
    enderror
    0.88
    
    0.57
    XmlAccessType
    0.57
     transfieras
    0.56
     فريبيس
    0.55
    hoga
    0.55
    GEBURTSDATUM
    0.53
    RefNanny
    0.53
     Alley
    0.52
     referenties
    0.52
    Activations Density 1.522%

    No Known Activations