© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10539
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to past connections or reunions of people.

    oai_token-act-pair · gemini-2.0-flash

    relationships and connections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    <bos>
    -0.58
    AutoSize
    -0.52
    ciating
    -0.48
    tront
    -0.47
    товано
    -0.44
     trinh
    -0.43
     ederim
    -0.42
     print
    -0.42
    print
    -0.41
     pernas
    -0.41
    POSITIVE LOGITS
    igshid
    0.74
     समीक्षक
    0.69
     EnglishChoose
    0.60
    EndContext
    0.60
     Mej
    0.58
    Geplaatst
    0.58
    setAccessible
    0.57
    makeConstraints
    0.55
    AsUp
    0.55
    GEBURTSDATUM
    0.55
    Activations Density 0.717%

    No Known Activations