© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5682
    Prev
    Next
    INDEX
    Explanations

    words relating to pagan or early religious beliefs, mythology, and astronomy

    oai_token-act-pair · gemini-2.0-flash

    Celestial objects

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     M
    -0.49
     E
    -0.47
     L
    -0.47
     So
    -0.43
     Me
    -0.43
     A
    -0.43
    RELATED
    -0.41
     satunya
    -0.41
     K
    -0.41
     penutup
    -0.41
    POSITIVE LOGITS
     comets
    0.81
     volcano
    0.81
     rockets
    0.81
     volcanoes
    0.81
     mergeFrom
    0.80
     تضيفلها
    0.80
    хьтан
    0.79
     Stonehenge
    0.79
     missiles
    0.79
     Cæsar
    0.78
    Activations Density 5.472%

    No Known Activations