© 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. 12250
    Prev
    Next
    INDEX
    Explanations

    verbs related to conflict, either interpersonal or physical, as well as terms related to legal, political, and medical conflict.

    oai_token-act-pair · 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
     ourselves
    -0.84
    selves
    -0.65
     Lordships
    -0.59
    XMLSchema
    -0.56
    我们的
    -0.56
    我們的
    -0.55
     שלנו
    -0.55
     Siamo
    -0.55
    Our
    -0.54
    mtrl
    -0.54
    POSITIVE LOGITS
     his
    0.82
    <bos>
    0.68
    aarrggbb
    0.65
     himself
    0.62
    his
    0.60
     hänen
    0.60
     تانيه
    0.59
     مُعرِّف
    0.59
     seines
    0.58
     seinem
    0.56
    Activations Density 6.669%

    No Known Activations