© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13039
    Prev
    Next
    INDEX
    Explanations

    French words commonly used in conversation and online forums

    oai_token-act-pair · gemini-2.0-flash

    par

    np_max-act · gemini-2.0-flash

    par

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    TypedDataSet
    -0.73
     EconPapers
    -0.63
    StructEnd
    -0.60
    chtes
    -0.57
    MLLoader
    -0.57
    GEBURTSDATUM
    -0.56
    WithIOException
    -0.54
     geldig
    -0.52
    atschappij
    -0.52
    قایناق‌لار
    -0.51
    POSITIVE LOGITS
     bave
    0.61
    imod
    0.60
    érons
    0.60
     CRI
    0.59
    }\]
    0.58
    odora
    0.57
    çam
    0.57
     FetchType
    0.57
     Jpa
    0.57
    tréal
    0.56
    Activations Density 0.548%

    No Known Activations