© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9811
    Prev
    Next
    INDEX
    Explanations

    medical actions that are performed on living beings

    oai_token-act-pair · gemini-2.0-flash

    scientific texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    Autoritní
    -0.69
    elemField
    -0.64
    aarrggbb
    -0.63
    Manfaat
    -0.58
    TestingModule
    -0.58
    IndentedString
    -0.58
     uintptr
    -0.57
    хьтан
    -0.56
    oneofs
    -0.56
     initComponents
    -0.55
    POSITIVE LOGITS
    chkin
    0.66
     gratuitement
    0.48
    Referències
    0.47
     EnglishChoose
    0.47
     ترین
    0.45
    CrossRef
    0.45
     ولد
    0.45
    ítése
    0.43
    gië
    0.42
    fra
    0.42
    Activations Density 1.535%

    No Known Activations