© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3364
    Prev
    Next
    INDEX
    Explanations

    words and short phrases related to court proceedings, software interfaces, and text messages in various languages.

    oai_token-act-pair · gemini-2.0-flash

    computers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     utafitiHapana
    -0.62
    цездатний
    -0.60
    脚注の使い方
    -0.56
    Географија
    -0.52
     vPvB
    -0.51
    MemoryWarning
    -0.50
     дописавши
    -0.48
     Faso
    -0.47
     MainAxisSize
    -0.47
    әрмәләр
    -0.47
    POSITIVE LOGITS
     CreateTagHelper
    0.70
    InSection
    0.58
    orical
    0.58
    LayoutConstraint
    0.57
    setVerticalGroup
    0.56
    وفة
    0.56
    styleable
    0.56
    gians
    0.55
    NOPQRST
    0.54
     referenties
    0.53
    Activations Density 19.429%

    No Known Activations