© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10116
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially those with backticks, colons, and the word "example".

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
    RTLR
    -0.62
    orianCalendar
    -0.57
    UnusedPrivate
    -0.51
    AutoField
    -0.50
    StoryboardSegue
    -0.50
    mulos
    -0.47
    HasForeignKey
    -0.47
     CreateTagHelper
    -0.46
    writeFieldEnd
    -0.46
    complexContent
    -0.45
    POSITIVE LOGITS
    Referanser
    0.60
    TagMode
    0.59
    stdafx
    0.54
     déplacements
    0.54
     traités
    0.53
    ViewInit
    0.52
    を切り
    0.52
    ilustrasi
    0.52
    [--
    0.51
     fermés
    0.50
    Activations Density 2.031%

    No Known Activations