© 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. 6460
    Prev
    Next
    INDEX
    Explanations

    the string "Person," regardless of the context

    oai_token-act-pair · gemini-2.0-flash

    Person

    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
    <bos>
    -1.10
    ↵↵
    -0.63
    okko
    -0.56
    interopRequire
    -0.56
    execSQL
    -0.51
    disposing
    -0.49
    قرير
    -0.49
    +#+#
    -0.48
    弁
    -0.47
     obrazu
    -0.47
    POSITIVE LOGITS
    adaptiveStyles
    0.63
    SharedCtor
    0.57
    летний
    0.54
    DockStyle
    0.54
    InSection
    0.54
    kými
    0.54
     propOrder
    0.52
    
    0.52
     Chwiliwch
    0.52
    ifolium
    0.50
    Activations Density 1.717%

    No Known Activations