© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14388
    Prev
    Next
    INDEX
    Explanations

    code snippets and code-related terms

    oai_token-act-pair · gemini-2.0-flash

    using

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    AndEndTag
    -0.88
     BoxDecoration
    -0.84
     الحره
    -0.81
    }\]
    -0.78
    BufferException
    -0.78
     Мексичка
    -0.78
    DoubleQuotes
    -0.77
    QMetaType
    -0.77
    PreferredItem
    -0.77
    aarrggbb
    -0.72
    POSITIVE LOGITS
     Roskov
    0.67
    hoeddwyd
    0.56
    aff
    0.46
     ',',
    0.43
    KeySpec
    0.41
     Valley
    0.39
     median
    0.39
     Foul
    0.38
     International
    0.38
    even
    0.37
    Activations Density 2.713%

    No Known Activations