© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12290
    Prev
    Next
    INDEX
    Explanations

    phrases related to the depletion of resources such as time or supplies.

    oai_token-act-pair · gemini-2.0-flash

    variations of the verb "run"

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

    run

    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
     AttributeSet
    -0.55
    intios
    -0.50
     []:
    -0.49
    henswürdigkeiten
    -0.48
    ServletException
    -0.46
    InputBorder
    -0.46
     getchar
    -0.46
    GraphicsUnit
    -0.46
    IUrlHelper
    -0.45
     <=",
    -0.42
    POSITIVE LOGITS
     run
    2.45
     running
    2.38
     runs
    2.33
     ran
    2.33
     Running
    2.25
     Run
    2.17
    Running
    2.13
     Runs
    2.11
    run
    2.09
    Run
    2.09
    Activations Density 1.109%

    No Known Activations