© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13247
    Prev
    Next
    INDEX
    Explanations

    various elements of source code, including comments, preprocessor directives, and struct definitions

    oai_token-act-pair · gemini-2.0-flash

    technical programming terms or file types

    np_token-act-pair-logits · gpt-4o-mini

    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_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    WEBPACK
    -0.56
    chitis
    -0.54
    AutoScaleMode
    -0.54
    HasBeenSet
    -0.53
    LayoutStyle
    -0.48
    hoea
    -0.48
    sizeCache
    -0.48
     Seeder
    -0.47
    volver
    -0.46
    persky
    -0.46
    POSITIVE LOGITS
    ftagPool
    0.55
     gawas
    0.47
    stam
    0.47
     Infórmanos
    0.46
     électriques
    0.46
     dequeue
    0.45
     bald
    0.45
    arch
    0.45
     religieuse
    0.44
    cshtml
    0.44
    Activations Density 1.940%

    No Known Activations