© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11092
    Prev
    Next
    INDEX
    Explanations

    sentences where two or more people co-exist, interact, are related, or are otherwise together.

    oai_token-act-pair · gemini-2.0-flash

    plural pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     gemeinsamen
    -0.57
     together
    -0.56
     совмест
    -0.56
     juntos
    -0.54
     gemeinsame
    -0.51
     mutual
    -0.50
     miteinander
    -0.48
    お互
    -0.47
     Together
    -0.47
     conjunta
    -0.47
    POSITIVE LOGITS
    tagHelperRunner
    0.90
     estekak
    0.88
    makeConstraints
    0.87
    
    0.82
     Normdatei
    0.82
    MLLoader
    0.80
    UserScript
    0.75
    webElementXpaths
    0.73
     صوتيه
    0.73
    SBATCH
    0.73
    Activations Density 1.139%

    No Known Activations