© 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. 1966
    Prev
    Next
    INDEX
    Explanations

    code snippets in a variety of programming languages

    oai_token-act-pair · gemini-2.0-flash

    parentheses

    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
     verlassen
    -0.49
    [
    -0.48
    ENTA
    -0.46
     
    -0.45
    Carreira
    -0.43
     [
    -0.43
     chí
    -0.43
    нето
    -0.42
    سع
    -0.42
    gathered
    -0.42
    POSITIVE LOGITS
     Monfieur
    0.89
     myſelf
    0.88
    DeleteBehavior
    0.87
     fubject
    0.86
     Majefty
    0.85
    ImageContext
    0.82
     leaſt
    0.82
     whoſe
    0.81
     raiſ
    0.81
    ()):
    0.81
    Activations Density 0.977%

    No Known Activations