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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8592
    Prev
    Next
    INDEX
    Explanations

    words related to column-based data in data tables and spreadsheets

    oai_token-act-pair · gemini-2.0-flash

    table data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    存于互联网档案馆
    -0.54
    ukone
    -0.52
    ValueStyle
    -0.47
    ✭✭
    -0.46
    ագրություններ
    -0.46
     EconPapers
    -0.45
    ⓧ
    -0.45
    lujah
    -0.44
     htons
    -0.43
     Walkover
    -0.43
    POSITIVE LOGITS
     étoit
    0.73
     enfans
    0.68
     auroit
    0.67
     figliu
    0.67
     médicaux
    0.66
     ainfi
    0.62
     feroit
    0.61
     étoient
    0.61
     auffi
    0.60
     pouvoit
    0.60
    Activations Density 44.601%

    No Known Activations