© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11489
    Prev
    Next
    INDEX
    Explanations

    the word "forces" in the context of military action

    oai_token-act-pair · gemini-2.0-flash

    forces

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    displaystyle
    -0.64
     forces
    -0.53
     gap
    -0.49
     force
    -0.45
     @
    -0.45
     dos
    -0.44
     team
    -0.43
    gap
    -0.43
     
    -0.42
     day
    -0.42
    POSITIVE LOGITS
     Efq
    1.02
     Jefus
    0.81
    DockStyle
    0.79
     Shakspeare
    0.79
     Majefty
    0.78
     pleaſure
    0.77
     تضيفلها
    0.76
     leſs
    0.74
     ftate
    0.74
     myſelf
    0.74
    Activations Density 0.825%

    No Known Activations