© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2578
    Prev
    Next
    INDEX
    Explanations

    references to prior work, often patents, studies or papers, and verbs related to describing or studying something

    oai_token-act-pair · gemini-2.0-flash

    scientific descriptions/disclosures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    ++]
    -0.53
     barbati
    -0.53
     zaměst
    -0.52
     deschis
    -0.51
     señ
    -0.51
     álcool
    -0.49
     virš
    -0.49
     tế
    -0.48
     raisonnable
    -0.47
     putem
    -0.47
    POSITIVE LOGITS
    <bos>
    1.22
    awtextra
    0.61
    rouvez
    0.61
    adaptiveStyles
    0.60
    InjectAttribute
    0.59
     autorytatywna
    0.58
     незавершена
    0.58
    rawDesc
    0.56
     Electra
    0.56
     चीज़ों
    0.56
    Activations Density 5.516%

    No Known Activations