© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7387
    Prev
    Next
    INDEX
    Explanations

    scientific writing, including numbers, citations, data analysis, experiments, and lab results, often in the context of a meta-analysis or research study.

    oai_token-act-pair · gemini-2.0-flash

    Numbers (Tens/Hundreds)

    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
     three
    -1.95
    three
    -1.77
     four
    -1.75
    Three
    -1.61
     trois
    -1.55
     THREE
    -1.52
     Three
    -1.51
    four
    -1.48
     drei
    -1.44
     três
    -1.41
    POSITIVE LOGITS
    hundred
    0.59
     hundred
    0.59
     Twenty
    0.56
     Tenth
    0.56
     Hundred
    0.56
     tenth
    0.56
     Sixty
    0.56
     decade
    0.55
     Thirty
    0.55
     Fifty
    0.54
    Activations Density 12.117%

    No Known Activations