© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10480
    Prev
    Next
    INDEX
    Explanations

    instances of "set" or "setting" followed by some object

    oai_token-act-pair · gemini-2.0-flash

    setting or establishing actions/goals

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

    set

    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
     set
    -0.75
    set
    -0.62
     Set
    -0.59
    ագրություններ
    -0.56
    Set
    -0.56
    bootstrapcdn
    -0.50
     sett
    -0.48
     SET
    -0.46
    mybatisplus
    -0.45
    Dichloropropene
    -0.44
    POSITIVE LOGITS
     up
    0.79
    وصلات
    0.59
    endforeach
    0.56
     aside
    0.56
     مشين
    0.55
     препратки
    0.54
    ecuzione
    0.54
    帖最后由
    0.54
     proper
    0.53
    styleType
    0.53
    Activations Density 3.818%

    No Known Activations