© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11723
    Prev
    Next
    INDEX
    Explanations

    language related to finance

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    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
    StructEnd
    -0.69
     investment
    -0.62
    VersionUID
    -0.59
    ंदीखरीदारी
    -0.59
     AssemblyTitle
    -0.57
     market
    -0.55
     vectorielle
    -0.54
    MockBean
    -0.54
     dévelo
    -0.54
    Източници
    -0.54
    POSITIVE LOGITS
     szóci
    0.54
     hear
    0.54
     bài
    0.51
    ifoli
    0.51
     Net
    0.50
    cydow
    0.48
     imagine
    0.47
     Вікіпе
    0.46
     story
    0.46
    Net
    0.46
    Activations Density 8.925%

    No Known Activations