© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3268
    Prev
    Next
    INDEX
    Explanations

    dates in a variety of formats within legal documents

    oai_token-act-pair · gemini-2.0-flash

    Dates and legal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ceras
    -0.43
    håll
    -0.41
     estre
    -0.41
     fell
    -0.40
    kloped
    -0.40
     fechado
    -0.39
    charAt
    -0.39
     gereja
    -0.38
     namanya
    -0.38
    here
    -0.37
    POSITIVE LOGITS
     ModelExpression
    0.71
     {}".
    0.69
    GOTREF
    0.68
     {}'.
    0.67
    contentLoaded
    0.67
    íncia
    0.66
    MLLoader
    0.66
    ValueStyle
    0.65
     scissors
    0.64
     متعلقه
    0.63
    Activations Density 0.781%

    No Known Activations