© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10523
    Prev
    Next
    INDEX
    Explanations

    words related to Islam, the Middle East, and/or violence

    oai_token-act-pair · gemini-2.0-flash

    Prophet or Arab

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    حياتها
    -0.63
     AssemblyProduct
    -0.60
    حياته
    -0.56
    <bos>
    -0.54
     Morley
    -0.52
     hæ
    -0.50
    المكان
    -0.50
     rodo
    -0.50
    unmodifiable
    -0.49
     considérons
    -0.49
    POSITIVE LOGITS
    хьтан
    0.68
    Portale
    0.65
    aneamente
    0.60
     InputDecoration
    0.59
    alyptus
    0.57
    StringProperty
    0.55
    ViewStyle
    0.54
     Aung
    0.53
    près
    0.52
     transférez
    0.52
    Activations Density 0.126%

    No Known Activations