© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6349
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially C++/C#/swift

    oai_token-act-pair · gemini-2.0-flash

    brackets/braces

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    SharedCtor
    -0.59
     chi̍t
    -0.57
    ensement
    -0.50
    tagHelperRunner
    -0.49
    НИК
    -0.49
    opardy
    -0.49
    ]<<"
    -0.48
    Diweddarwch
    -0.48
    :✨
    -0.47
    Firm
    -0.46
    POSITIVE LOGITS
    Източници
    0.57
     actionMode
    0.54
    ("]");
    0.53
     skippy
    0.52
    Einzelnachweise
    0.51
    labili
    0.50
    protoc
    0.50
    bemos
    0.49
    jsoup
    0.48
    retudo
    0.48
    Activations Density 8.306%

    No Known Activations