© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12615
    Prev
    Next
    INDEX
    Explanations

    substrings from Indian names

    oai_token-act-pair · gemini-2.0-flash

    Formal Writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     means
    -0.43
    routs
    -0.43
     marque
    -0.42
    ichiro
    -0.40
    Erstellt
    -0.40
    égorie
    -0.39
    means
    -0.38
    atet
    -0.38
    otomy
    -0.38
     świad
    -0.38
    POSITIVE LOGITS
     NSCoder
    0.72
    ंदीखरीदारी
    0.72
     Meksiku
    0.71
    PyExc
    0.70
    TagMode
    0.69
     فريبيس
    0.66
     tamil
    0.66
     Chaldean
    0.65
     otomatig
    0.63
    Tamil
    0.62
    Activations Density 0.207%

    No Known Activations