© 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. 10522
    Prev
    Next
    INDEX
    Explanations

    words that look like they could be relevant to academia, research, and biological sciences

    oai_token-act-pair · gemini-2.0-flash

    scientific/technical language

    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
    o
    -1.09
    oc
    -0.96
    о
    -0.95
    OC
    -0.95
    ｏ
    -0.94
    ot
    -0.94
    oj
    -0.93
    OF
    -0.92
    otu
    -0.92
    OL
    -0.91
    POSITIVE LOGITS
    betical
    0.38
    irmish
    0.37
    ItemBackground
    0.36
    ěst
    0.36
     Yarm
    0.35
    assemblée
    0.35
    blind
    0.35
     azy
    0.33
    UVEN
    0.33
    uyện
    0.33
    Activations Density 0.897%

    No Known Activations