© 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. 12733
    Prev
    Next
    INDEX
    Explanations

    words related to measurement, officiality, and quantity

    oai_token-act-pair · gemini-2.0-flash

    Middle East / Asia locations

    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
    +#+#
    -0.71
    UnusedPrivate
    -0.60
    ThroughAttribute
    -0.60
     vägen
    -0.57
    webElementXpaths
    -0.56
    parsedMessage
    -0.56
     americanos
    -0.56
    RegressionTest
    -0.56
    참고
    -0.56
     igång
    -0.56
    POSITIVE LOGITS
     يتيمه
    0.64
    hore
    0.53
     Mosque
    0.52
     Lahore
    0.52
     mosque
    0.51
    sheng
    0.49
     Sule
    0.49
     Bho
    0.49
     Sindh
    0.48
     NGO
    0.47
    Activations Density 11.118%

    No Known Activations