© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5744
    Prev
    Next
    INDEX
    Explanations

    parentheses, numbers and some words that could be found in scientific publications

    oai_token-act-pair · gemini-2.0-flash

    Parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     متعلقه
    -0.78
     _)
    -0.77
    ();)
    -0.77
    __(/*!
    -0.71
    afficheront
    -0.71
    ?).
    -0.69
    WriteTagHelper
    -0.69
    ientôt
    -0.69
    )”.
    -0.68
    SharedCtor
    -0.68
    POSITIVE LOGITS
    قایناق‌لار
    0.54
    bkz
    0.46
    Референце
    0.45
     promise
    0.44
     travaillons
    0.41
    Hauptartikel
    0.40
    labelText
    0.40
     odkazy
    0.40
    HasIndex
    0.40
    liwości
    0.40
    Activations Density 2.325%

    No Known Activations