© 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. 6234
    Prev
    Next
    INDEX
    Explanations

    code-like text, especially that involving file transfer, raw data, and GitHub

    oai_token-act-pair · gemini-2.0-flash

    code and urls

    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
    ↵↵
    -0.63
    ge
    -0.58
    2
    -0.55
    <bos>
    -0.54
    is
    -0.53
    <h2>
    -0.51
    1
    -0.50
    ↵
    -0.50
     in
    -0.49
     is
    -0.48
    POSITIVE LOGITS
     ainfi
    1.14
     Theſe
    1.10
     feroit
    1.04
     malheure
    1.03
     zelve
    1.01
     '{@
    1.01
     myſelf
    1.01
     pouvoit
    1.00
     Anſ
    1.00
     purpoſe
    0.99
    Activations Density 1.864%

    No Known Activations