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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1386
    Prev
    Next
    INDEX
    Explanations

    a mix of programming code, scientific writing about semiconductors, and scientific writing about statistical bias

    oai_token-act-pair · gemini-2.0-flash

    technical code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     propOrder
    -0.93
    sizeCache
    -0.74
    EndGlobalSection
    -0.63
    stateProvider
    -0.60
     Roskov
    -0.56
    StructEnd
    -0.52
    !*\
    -0.51
     通販
    -0.51
    fjspx
    -0.51
     resourceCulture
    -0.50
    POSITIVE LOGITS
    NUMX
    0.56
    oucí
    0.52
     ब्रेकडाउन
    0.51
    IFORNIA
    0.50
    können
    0.49
    WAUKEE
    0.49
    }{*}{}
    0.48
    
    0.48
    IsContent
    0.48
    первых
    0.47
    Activations Density 10.011%

    No Known Activations