© 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. 11527
    Prev
    Next
    INDEX
    Explanations

    code snippets and configurations, including conditional statements and variable visibility keywords

    oai_token-act-pair · gemini-2.0-flash

    Cond

    np_max-act · gemini-2.0-flash

    Cond

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     Kitz
    -0.61
     Monfieur
    -0.59
     CreateTagHelper
    -0.59
    arXiv
    -0.57
     Shakspeare
    -0.56
    itrile
    -0.54
     Efq
    -0.54
     Infir
    -0.54
    AllAfrica
    -0.54
     fevere
    -0.52
    POSITIVE LOGITS
    <bos>
    1.07
     للاسماء
    0.63
    UnusedPrivate
    0.52
     ivelany
    0.52
    المكان
    0.51
     resourceCulture
    0.50
    QMetaType
    0.48
     Autorizaciones
    0.48
    Cyfarwyddwr
    0.48
    RRect
    0.47
    Activations Density 1.810%

    No Known Activations