© 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. 7826
    Prev
    Next
    INDEX
    Explanations

    mentions of religion coupled with uncertainty

    oai_token-act-pair · gemini-2.0-flash

    Religion

    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
     GenerationType
    -0.79
    ModelAdmin
    -0.77
    sizeCache
    -0.73
     الرياضيه
    -0.66
    tagHelperRunner
    -0.66
    IntoConstraints
    -0.63
    SequentialGroup
    -0.63
     متعلقه
    -0.61
    Населення
    -0.60
    HtmlAttribute
    -0.59
    POSITIVE LOGITS
    elt
    0.51
    Atoi
    0.50
    zelle
    0.49
     Believe
    0.47
     spell
    0.47
    odiment
    0.46
    liwości
    0.45
    ]--;
    0.44
    Believe
    0.44
    кация
    0.43
    Activations Density 5.331%

    No Known Activations