© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8339
    Prev
    Next
    INDEX
    Explanations

    instances of the words "bread" and "pray"

    oai_token-act-pair · gemini-2.0-flash

    faith, food

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     
    -0.54
    ↵↵
    -0.54
    ability
    -0.49
    )}-\
    -0.48
     The
    -0.47
     end
    -0.44
    lasty
    -0.44
    a
    -0.43
    ed
    -0.43
    i
    -0.43
    POSITIVE LOGITS
     FetchType
    1.19
    NUMX
    1.13
    Personensuche
    1.04
     المعيارى
    1.01
     فريبيس
    1.00
    tvguidetime
    0.95
     виправивши
    0.94
    ngdoc
    0.91
    endpush
    0.90
    XmlAccessorType
    0.90
    Activations Density 0.512%

    No Known Activations