© 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. 6051
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate something is being added to something else, particularly in the context of a study.

    oai_token-act-pair · gemini-2.0-flash

    technical terms related to scientific studies

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

    scientific studies involving supplements

    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
    ✨:
    -0.59
    swire
    -0.55
    posito
    -0.50
    rophoto
    -0.50
    บาย
    -0.49
    clusal
    -0.49
    abestanden
    -0.48
     pool
    -0.48
    rops
    -0.47
     cherchés
    -0.47
    POSITIVE LOGITS
    matchCondition
    0.65
    AndroidJUnit
    0.55
    saraba
    0.52
     հղումներ
    0.52
     egiten
    0.52
    RuleContext
    0.51
     Bioaccumulative
    0.51
    Schedulers
    0.50
    TestBed
    0.49
     resourceCulture
    0.48
    Activations Density 2.019%

    No Known Activations