© 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. 13392
    Prev
    Next
    INDEX
    Explanations

    uses of the word "force" in technical writing, particularly related to physics or mechanics

    oai_token-act-pair · gemini-2.0-flash

    forced actions

    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
     force
    -2.75
     Force
    -2.70
    Force
    -2.64
    force
    -2.61
     FORCE
    -2.59
     forces
    -2.36
     Forces
    -2.33
    FORCE
    -2.28
    forces
    -2.27
    Forces
    -2.25
    POSITIVE LOGITS
    HasForeignKey
    0.54
    GEBURTSDATUM
    0.48
    NewGuid
    0.43
    يكب
    0.42
    بوابة
    0.41
    QUER
    0.41
    บรร
    0.40
    ūra
    0.39
    WithIdentifier
    0.39
    gogo
    0.39
    Activations Density 2.291%

    No Known Activations