© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3630
    Prev
    Next
    INDEX
    Explanations

    words related to legal disputes, competition, or pressure

    oai_token-act-pair · gemini-2.0-flash

    against

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Himo
    -0.81
     poffe
    -0.81
    RenderAtEndOf
    -0.76
     myſelf
    -0.75
     occaf
    -0.71
    makeConstraints
    -0.71
    niająca
    -0.70
     pleaſure
    -0.70
     ujednoznacz
    -0.69
     themſelves
    -0.68
    POSITIVE LOGITS
     against
    2.52
    against
    2.09
     Against
    2.02
     contre
    1.98
    Against
    1.95
     gegen
    1.84
     AGAINST
    1.77
     contra
    1.73
     tegen
    1.69
     против
    1.63
    Activations Density 2.909%

    No Known Activations