© 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. 8451
    Prev
    Next
    INDEX
    Explanations

    sentences where someone is describing their goals or intentions about improving some general skill.

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "work"

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

    working

    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
    sidemargin
    -0.83
     saites
    -0.71
    BeginContext
    -0.71
    存于互联网档案馆
    -0.69
    mybatisplus
    -0.64
    UrlResolution
    -0.61
     Offisielt
    -0.61
    chließ
    -0.60
     Himo
    -0.59
    RenderAtEndOf
    -0.59
    POSITIVE LOGITS
     work
    2.61
    work
    2.33
     Work
    2.31
    Work
    2.30
     working
    2.23
     worked
    2.23
     WORK
    2.17
    working
    2.11
    worked
    2.05
    WORK
    2.03
    Activations Density 1.457%

    No Known Activations