© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9407
    Prev
    Next
    INDEX
    Explanations

    code referencing the System.Windows.Forms namespace, especially relating to UI elements like panels and their properties

    oai_token-act-pair · gemini-2.0-flash

    code and forms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    انيف
    -0.57
    InjectAttribute
    -0.50
     DISCIP
    -0.49
    featureID
    -0.48
    ben
    -0.47
    IndentedString
    -0.47
    IUrlHelper
    -0.45
    writeField
    -0.45
     compréhen
    -0.45
     Geset
    -0.45
    POSITIVE LOGITS
    IntoConstraints
    0.78
    帖最后由
    0.73
    tvguidetime
    0.66
    AndEndTag
    0.59
    DispatchToProps
    0.59
     saites
    0.57
    ⋙
    0.54
    הערות
    0.53
     PPS
    0.52
     Newswire
    0.51
    Activations Density 1.097%

    No Known Activations