© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12721
    Prev
    Next
    INDEX
    Explanations

    news reports concerning international conflict, political violence, or terrorism, particularly focusing on casualties.

    oai_token-act-pair · gemini-2.0-flash

    death, violence, arrests

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     autorytatywna
    -0.69
     trajets
    -0.67
    expandindo
    -0.65
    BufferException
    -0.62
     '\\;'
    -0.60
    RegistryLite
    -0.59
    }\]
    -0.59
    AddTagHelper
    -0.59
    Filmographie
    -0.59
    "});
    -0.58
    POSITIVE LOGITS
    Pur
    0.51
     rounded
    0.50
     killed
    0.47
     present
    0.46
    円で
    0.45
    +:+
    0.45
     advantage
    0.44
     who
    0.44
    pur
    0.44
     congratulate
    0.44
    Activations Density 4.011%

    No Known Activations