© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12449
    Prev
    Next
    INDEX
    Explanations

    locations in Maine, especially correctional facilities

    oai_token-act-pair · gemini-2.0-flash

    Penobscot County Jail

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    عنوان
    -0.45
     dummies
    -0.44
    穷
    -0.41
    ához
    -0.41
     Solidity
    -0.41
    ыгана
    -0.41
    窮
    -0.41
    siasme
    -0.40
    RefNanny
    -0.40
     Gaspar
    -0.40
    POSITIVE LOGITS
    Oregon
    0.75
    
    0.75
     Oregon
    0.72
     nahilalakip
    0.71
    kuuta
    0.71
     OREGON
    0.71
    matchCondition
    0.69
    Cyfeiriadau
    0.68
    batore
    0.68
     חיצוניים
    0.68
    Activations Density 0.509%

    No Known Activations