© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4773
    Prev
    Next
    INDEX
    Explanations

    language related to counter-terrorism initiatives

    oai_token-act-pair · gemini-2.0-flash

    terrorism and extremism

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     conflict
    -0.82
     war
    -0.75
     conflit
    -0.73
     civil
    -0.70
     conflits
    -0.69
     guerra
    -0.68
     guerre
    -0.68
     Civil
    -0.68
     conflicts
    -0.64
    Civil
    -0.63
    POSITIVE LOGITS
     nahilalakip
    0.80
    addCriterion
    0.77
     protoimpl
    0.71
    AddHtmlAttribute
    0.69
    oneofs
    0.64
     lenker
    0.63
    expandindo
    0.63
    ⓧ
    0.63
     BrowserModule
    0.61
     Counter
    0.60
    Activations Density 0.967%

    No Known Activations