© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 2378
    Prev
    Next
    INDEX
    Explanations

    the phrase "driving force"

    oai_token-act-pair · gemini-2.0-flash

    the word "force"

    np_token-act-pair-logits · gpt-4o-mini

    force

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    neté
    -0.56
    réhen
    -0.53
     StatefulWidget
    -0.51
     vPvB
    -0.47
    owieck
    -0.46
    IService
    -0.46
    sprechend
    -0.46
    SqlSession
    -0.45
    krish
    -0.44
    생
    -0.44
    POSITIVE LOGITS
     force
    2.09
     forces
    2.03
    force
    1.70
    forces
    1.70
     Forces
    1.54
     FORCES
    1.48
     Force
    1.48
    Force
    1.46
    Forces
    1.45
     FORCE
    1.44
    Activations Density 1.924%

    No Known Activations