© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4133
    Prev
    Next
    INDEX
    Explanations

    words related to violence and conflict, often including casualties and involved parties.

    oai_token-act-pair · gemini-2.0-flash

    Death and loss of life

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    DebuggerNonUser
    -0.74
     Monza
    -0.55
     fag
    -0.53
     Aene
    -0.52
    ocie
    -0.52
    Hochspringen
    -0.52
     Baillargeon
    -0.50
    ciato
    -0.50
     sats
    -0.49
    steuer
    -0.49
    POSITIVE LOGITS
     onOptions
    0.56
    #+#
    0.54
    Bronnen
    0.52
    Décès
    0.51
     casualties
    0.51
     незавершена
    0.48
     AssemblyCompany
    0.47
    eachtet
    0.47
    PerformLayout
    0.46
     createSlice
    0.46
    Activations Density 1.310%

    No Known Activations