© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3779
    Prev
    Next
    INDEX
    Explanations

    code snippets, code documentation, and technical lingo

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act · gemini-2.0-flash

    punctuation

    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_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
     purpoſe
    -2.08
     Majefty
    -1.97
     Efq
    -1.94
     myſelf
    -1.93
     ſeveral
    -1.91
     himſelf
    -1.88
     Reſ
    -1.88
     pleaſure
    -1.88
     houſe
    -1.87
     itſelf
    -1.87
    POSITIVE LOGITS
    <bos>
    1.38
    ↵
    1.29
    ↵↵
    1.21
    '
    1.06
    。
    0.91
    <eos>
    0.91
    （
    0.88
    ，
    0.87
    ？
    0.81
    "
    0.80
    Activations Density 2.480%

    No Known Activations