© 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. 4950
    Prev
    Next
    INDEX
    Explanations

    java code that uses JTextField and getText

    oai_token-act-pair · gemini-2.0-flash

    programming code

    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
    windowFixed
    -0.83
    ConstraintMaker
    -0.82
    addCriterion
    -0.81
     <=",
    -0.80
     ddelweddau
    -0.77
    TestingModule
    -0.77
    verwijspagina
    -0.74
     الرياضيه
    -0.71
    Jîn
    -0.71
    rungsseite
    -0.71
    POSITIVE LOGITS
    TagHelpers
    0.43
     getir
    0.39
    ฐาน
    0.39
    ンス
    0.36
    geted
    0.35
     summer
    0.35
    เทศ
    0.35
     opie
    0.35
     geti
    0.35
    #
    0.35
    Activations Density 0.628%

    No Known Activations