© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14820
    Prev
    Next
    INDEX
    Explanations

    a mixed bag of numerical date formats, names, and strings that could be chemical compounds or parts of URLs

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     resourceCulture
    -0.73
     nakalista
    -0.66
     MenuView
    -0.63
    MLLoader
    -0.62
    NameInMap
    -0.62
    URLException
    -0.59
    GEBURTSDATUM
    -0.59
    RenderAtEndOf
    -0.58
     numberWith
    -0.58
    !*\
    -0.58
    POSITIVE LOGITS
     con
    0.90
    Con
    0.56
    con
    0.56
     insuffisamment
    0.54
     Con
    0.51
    ScopeManager
    0.45
    質
    0.44
    دانشنامهٔ
    0.43
     cha
    0.43
    irim
    0.43
    Activations Density 1.142%

    No Known Activations