© 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. 9824
    Prev
    Next
    INDEX
    Explanations

    words and phrases within the context of depression and politics

    oai_token-act-pair · 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
     vœux
    -0.66
     auroit
    -0.65
     boî
    -0.65
    ArrowToggle
    -0.64
     négociations
    -0.63
     ainfi
    -0.63
     compréhen
    -0.63
     Paglinawan
    -0.63
     auffi
    -0.62
     quelcon
    -0.62
    POSITIVE LOGITS
     leads
    0.61
    ReusableCell
    0.52
     lead
    0.51
    PathVariable
    0.50
     pu
    0.49
    BufferException
    0.49
     thiệu
    0.47
     subs
    0.45
    LabelTagHelper
    0.45
     Mor
    0.45
    Activations Density 4.831%

    No Known Activations