© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3284
    Prev
    Next
    INDEX
    Explanations

    mentions of time and events

    oai_token-act-pair · gemini-2.0-flash

    time

    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
    цар
    -0.42
    <bos>
    -0.42
    ny
    -0.39
    тери
    -0.38
    عر
    -0.38
    <
    -0.38
    PrintStream
    -0.38
    ligt
    -0.37
    rantz
    -0.36
    By
    -0.36
    POSITIVE LOGITS
    WebServlet
    0.94
     beginnetje
    0.94
    awtextra
    0.91
     cherchés
    0.90
    клопе
    0.86
    +#+#
    0.81
     незавершена
    0.79
     فريبيس
    0.77
     ErrIntOverflow
    0.77
    #+#
    0.76
    Activations Density 2.974%

    No Known Activations