© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3099
    Prev
    Next
    INDEX
    Explanations

    code snippets with specific coding keywords and markup tags

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash

    programming identifiers

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    <bos>
    -0.54
    ρυ
    -0.29
     allAfrica
    -0.29
     VIDEOTAPE
    -0.28
    τι
    -0.27
    ropol
    -0.27
    kos
    -0.26
    pu
    -0.26
    rap
    -0.26
    tians
    -0.26
    POSITIVE LOGITS
     Efq
    0.48
     Monfieur
    0.46
     Majefty
    0.45
     purpoſe
    0.45
     myſelf
    0.45
     Theſe
    0.44
     ſeveral
    0.43
     himſelf
    0.41
     pleaſure
    0.41
     ſtate
    0.41
    Activations Density 34.868%

    No Known Activations