© 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. 10327
    Prev
    Next
    INDEX
    Explanations

    gibberish technical terms, including model names, product names, organization names, and some kinds of numbers

    oai_token-act-pair · gemini-2.0-flash

    Japanese product descriptions

    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
     المعيارى
    -0.73
    Autoritní
    -0.71
    Portail
    -0.70
    enumii
    -0.70
     lenker
    -0.69
    richTextPanel
    -0.66
    Iné
    -0.65
    ValueStyle
    -0.63
    ьаж
    -0.63
    writeField
    -0.63
    POSITIVE LOGITS
     sup
    0.38
    ')){
    0.36
     kanan
    0.36
    Nya
    0.36
     anyway
    0.35
     Sha
    0.35
     nya
    0.34
     credit
    0.34
     na
    0.34
    どうも
    0.34
    Activations Density 1.571%

    No Known Activations