© 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. 2596
    Prev
    Next
    INDEX
    Explanations

    references to Allah and religious concepts

    oai_token-act-pair · gemini-2.0-flash

    and

    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
    oa̍t
    -0.73
    XmlAccessType
    -0.70
     StatefulWidget
    -0.69
    ftagPool
    -0.68
    原始内容存档于
    -0.66
    出版年
    -0.65
     GenerationType
    -0.64
     ddelweddau
    -0.62
    GEBURTSDATUM
    -0.61
     HttpNotFound
    -0.60
    POSITIVE LOGITS
    jenost
    0.46
    AttributeName
    0.42
    angkutan
    0.42
     gomma
    0.42
    quién
    0.41
    nameof
    0.41
    }}}}
    0.41
     unwilling
    0.41
     hadas
    0.40
     milyon
    0.40
    Activations Density 9.984%

    No Known Activations