© 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. 10163
    Prev
    Next
    INDEX
    Explanations

    code snippets and references to UI elements like controllers, lists, and areas, as well as the word "Default"

    oai_token-act-pair · gemini-2.0-flash

    code

    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
     anticipo
    -0.48
     Pingback
    -0.46
    She
    -0.46
    nanoTime
    -0.46
    IntoConstraints
    -0.45
    تأ
    -0.45
     nido
    -0.45
     ?>>
    -0.44
    økt
    -0.44
    WriteLiteral
    -0.42
    POSITIVE LOGITS
    ///</
    0.71
    ieteur
    0.71
    ględ
    0.64
    ourke
    0.63
     AspNetCore
    0.61
    assertj
    0.60
    exao
    0.57
     postIndex
    0.57
    Bises
    0.57
    AMENT
    0.56
    Activations Density 0.220%

    No Known Activations