© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13850
    Prev
    Next
    INDEX
    Explanations

    words in a non-English language (possibly Malay) and words related to weddings

    oai_token-act-pair · gemini-2.0-flash

    Malaysia

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     '@/
    -0.65
     maxn
    -0.63
     NDEBUG
    -0.63
    BibitemShut
    -0.61
    =$?
    -0.60
    woll
    -0.60
     يتيمه
    -0.60
    ylde
    -0.59
    ärna
    -0.59
    ieson
    -0.58
    POSITIVE LOGITS
    Ber
    0.57
     sett
    0.55
     Ber
    0.52
    
    0.50
    ber
    0.47
    set
    0.46
    enumi
    0.46
     ber
    0.43
     Nadie
    0.42
     potest
    0.42
    Activations Density 0.184%

    No Known Activations