© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2395
    Prev
    Next
    INDEX
    Explanations

    code syntax such as parenthesis, brackets, quotation marks, and certain keywords

    oai_token-act-pair · gemini-2.0-flash

    code snippet

    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
    ContentAsync
    -0.66
     članak
    -0.63
     Ptolemy
    -0.60
    σθαι
    -0.59
    UALA
    -0.55
    źdz
    -0.55
    NewRow
    -0.54
    MessageOf
    -0.54
    antaranya
    -0.53
     Kef
    -0.53
    POSITIVE LOGITS
    <bos>
    0.85
     estimés
    0.57
    waitKey
    0.57
    NameInMap
    0.53
    StoryboardSegue
    0.51
    ніципа
    0.48
     yw
    0.48
    scrollY
    0.48
    ArrowToggle
    0.47
    msgSender
    0.47
    Activations Density 11.958%

    No Known Activations