© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5972
    Prev
    Next
    INDEX
    Explanations

    sentences that contain frequent usage of the word "be".

    oai_token-act-pair · gemini-2.0-flash

    discussion

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    jo
    -0.44
    ô
    -0.41
    lot
    -0.37
    sze
    -0.37
    jos
    -0.36
    به
    -0.35
    가
    -0.35
     Jo
    -0.35
    iter
    -0.35
    java
    -0.34
    POSITIVE LOGITS
     kaarangay
    1.15
    ValueStyle
    1.10
    GEBURTSDATUM
    1.09
     AssemblyProduct
    1.05
    JspWriter
    1.02
     Италијани
    1.02
    QMetaType
    0.97
     kasarigan
    0.97
    aarrggbb
    0.96
     snippetHide
    0.96
    Activations Density 0.578%

    No Known Activations