© 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. 4449
    Prev
    Next
    INDEX
    Explanations

    words relating to numbers, quantity, amount, or computation

    oai_token-act-pair · gemini-2.0-flash

    technical terms and programming concepts

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

    value

    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
    KommentareTeilen
    -0.67
    WebServlet
    -0.61
    ContentAlignment
    -0.59
    ″]
    -0.55
    urlpatterns
    -0.54
    stdc
    -0.54
    makeConstraints
    -0.52
    Originally
    -0.52
    式
    -0.51
     establishments
    -0.48
    POSITIVE LOGITS
     ModelExpression
    0.66
    FormTagHelper
    0.60
    uxxxx
    0.58
    าสตร์
    0.53
    はじめに
    0.52
    OnTop
    0.50
     సౌకర్య
    0.50
    ])));
    0.47
     fread
    0.46
    gaged
    0.46
    Activations Density 7.122%

    No Known Activations