© 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. 14232
    Prev
    Next
    INDEX
    Explanations

    research papers and data analysis.

    oai_token-act-pair · gemini-2.0-flash

    parts of a whole

    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
     AspNetCore
    -0.55
    kannya
    -0.54
     theirs
    -0.51
     tắt
    -0.48
     Dress
    -0.48
     dress
    -0.47
    γραφία
    -0.47
     Дата
    -0.47
     Bestand
    -0.47
    жешь
    -0.46
    POSITIVE LOGITS
     component
    0.91
     element
    0.91
    component
    0.90
    element
    0.78
     segment
    0.75
     subunit
    0.75
     Element
    0.75
    segment
    0.72
     chapter
    0.69
     ingredient
    0.69
    Activations Density 13.966%

    No Known Activations