© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2757
    Prev
    Next
    INDEX
    Explanations

    code in various programming languages

    oai_token-act-pair · gemini-2.0-flash

    programming keywords and functions

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

    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_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
    Personensuche
    -0.54
     <=",
    -0.51
    Lähteet
    -0.48
     ajoutez
    -0.48
    utilisons
    -0.47
    ApplicationTests
    -0.47
    onAttach
    -0.45
     NDEBUG
    -0.44
    +:+
    -0.44
    anglès
    -0.44
    POSITIVE LOGITS
     AttributeSet
    0.65
    pushFollow
    0.62
    numerusform
    0.60
    ClientRect
    0.60
    tomic
    0.57
    webElement
    0.56
    IBarButtonItem
    0.56
     ModelRenderer
    0.55
    kv
    0.54
    marle
    0.54
    Activations Density 2.279%

    No Known Activations