© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8721
    Prev
    Next
    INDEX
    Explanations

    words that relate to a workspace or office and collaboration

    oai_token-act-pair · gemini-2.0-flash

    words related to work and working

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

    work

    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
    ρεύ
    -0.56
    енча
    -0.54
     Савезне
    -0.53
     }}"></
    -0.52
     linkovi
    -0.51
    RegistryLite
    -0.50
    onOptions
    -0.50
     ""))
    -0.49
     chistes
    -0.49
     tearDown
    -0.49
    POSITIVE LOGITS
     work
    0.89
     working
    0.87
    working
    0.81
     Work
    0.81
    work
    0.77
     Working
    0.76
     WORKING
    0.74
    Work
    0.71
    Working
    0.70
     Trabaj
    0.70
    Activations Density 1.973%

    No Known Activations