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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2692
    Prev
    Next
    INDEX
    Explanations

    the prefix "du" followed by a few other possible letters to form "dukes", "duchy", or "dwarfs"

    oai_token-act-pair · gemini-2.0-flash

    du

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    writeFieldEnd
    -0.87
     صوتيه
    -0.80
    AxisAlignment
    -0.69
     EdgeInsets
    -0.63
    出版年
    -0.61
    RTLR
    -0.58
    MENAFN
    -0.58
     AssemblyCompany
    -0.58
     jadx
    -0.56
     TestBed
    -0.53
    POSITIVE LOGITS
    evos
    0.48
     semej
    0.46
     Manas
    0.45
     positifs
    0.45
    Viki
    0.44
    бовь
    0.44
     cref
    0.42
    号
    0.42
    Fue
    0.41
     Fue
    0.40
    Activations Density 0.169%

    No Known Activations