© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14614
    Prev
    Next
    INDEX
    Explanations

    C or similar code

    oai_token-act-pair · gemini-2.0-flash

    uint

    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
    keyColumn
    -0.57
     IconData
    -0.56
    ensan
    -0.54
    Zdroje
    -0.53
    PMailer
    -0.51
    最快更新
    -0.50
    DataSet
    -0.50
     scape
    -0.50
    enthe
    -0.50
    doms
    -0.49
    POSITIVE LOGITS
    enumii
    0.62
     Вікі
    0.59
     للمعارف
    0.58
    RectangleBorder
    0.58
    Controllo
    0.57
     autorytatywna
    0.53
    TintMode
    0.53
    resave
    0.52
    évaluateur
    0.50
     Erl
    0.50
    Activations Density 1.750%

    No Known Activations