© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10742
    Prev
    Next
    INDEX
    Explanations

    abbreviated names of proteins, antibodies, labs, and companies in a scientific context

    oai_token-act-pair · gemini-2.0-flash

    scientific and university context

    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
     autorytatywna
    -0.93
    addCriterion
    -0.61
    RenderAtEndOf
    -0.58
    Jeografia
    -0.53
    typography
    -0.53
    ViewFeatures
    -0.52
     EconPapers
    -0.52
     resourceCulture
    -0.51
    Identyfik
    -0.51
    Билгалдахарш
    -0.49
    POSITIVE LOGITS
    ypress
    0.47
    SuppressLint
    0.46
    memb
    0.46
     Hon
    0.46
    ]")]
    0.45
    ticides
    0.45
     Sixt
    0.44
    Unit
    0.44
    lettes
    0.44
    ACHUSET
    0.43
    Activations Density 1.322%

    No Known Activations