© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11626
    Prev
    Next
    INDEX
    Explanations

    HTML code related to links and stylesheets

    oai_token-act-pair · gemini-2.0-flash

    =

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     four
    -0.50
    imwrite
    -0.49
     kep
    -0.49
    byt
    -0.48
    ฬ
    -0.48
     link
    -0.47
     quatre
    -0.46
     eight
    -0.46
    нес
    -0.45
    گزاری
    -0.45
    POSITIVE LOGITS
     مشين
    0.82
    AccessorTable
    0.78
    ChildScrollView
    0.75
     surla
    0.69
     resourceCulture
    0.65
    <?
    0.65
    ształ
    0.64
     Dernière
    0.64
    rhosis
    0.63
     Réponses
    0.62
    Activations Density 0.338%

    No Known Activations