© 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. 13312
    Prev
    Next
    INDEX
    Explanations

    mentions of the United States, especially when abbreviated as "U.S."

    oai_token-act-pair · gemini-2.0-flash

    U.S

    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
     calendriers
    -0.65
    expandindo
    -0.63
     cherchés
    -0.59
    SourceChecksum
    -0.58
    __":
    -0.57
     Савезне
    -0.57
    __':
    -0.56
    nocześnie
    -0.54
    Datuak
    -0.54
     Wiktionnaire
    -0.52
    POSITIVE LOGITS
    TE
    0.55
    ZH
    0.54
    RAE
    0.54
    RA
    0.52
    AY
    0.52
    bede
    0.51
    MAA
    0.50
    TER
    0.50
    RET
    0.49
    CEA
    0.49
    Activations Density 6.778%

    No Known Activations