© 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. 12992
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to finances, electronic records, and official forms

    oai_token-act-pair · gemini-2.0-flash

    finance and taxes

    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
    WebVitals
    -0.77
    Jeografia
    -0.60
    @[+][
    -0.56
    "])
    -0.52
    inSlope
    -0.49
    zości
    -0.46
    ."],
    -0.46
    thansa
    -0.46
     Kv
    -0.45
    Sik
    -0.44
    POSITIVE LOGITS
     références
    0.66
     Administrativna
    0.65
    はじめに
    0.56
    
    0.54
     NFS
    0.52
     NSF
    0.51
     NFA
    0.50
     للمعارف
    0.49
     AssemblyTitle
    0.49
     betale
    0.49
    Activations Density 19.444%

    No Known Activations