© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10180
    Prev
    Next
    INDEX
    Explanations

    scientific publications mentioning results

    oai_token-act-pair · gemini-2.0-flash

    leads

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    ico
    -1.15
    ICO
    -0.96
    ica
    -0.66
    но
    -0.63
    reportWebVitals
    -0.61
    ICAL
    -0.55
     Tim
    -0.55
    cadeau
    -0.53
     sec
    -0.53
    iti
    -0.52
    POSITIVE LOGITS
     mukana
    0.71
    UpInside
    0.66
    MemoryWarning
    0.65
     ComVisible
    0.62
    ReusableCell
    0.61
    ebenarnya
    0.61
    queryInterface
    0.60
    AndEndTag
    0.58
    dropIfExists
    0.58
    melidir
    0.58
    Activations Density 3.778%

    No Known Activations