© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10311
    Prev
    Next
    INDEX
    Explanations

    mentions of gates of any form

    oai_token-act-pair · gemini-2.0-flash

    gate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     autorytatywna
    -0.81
     متعلقه
    -0.66
    expandindo
    -0.65
    underland
    -0.61
     OFDb
    -0.54
    ÍST
    -0.54
     المعيارى
    -0.54
    sividad
    -0.54
     مرئيه
    -0.54
    downarrow
    -0.53
    POSITIVE LOGITS
    AttributeSet
    0.62
    iconque
    0.60
    FAX
    0.57
    țiunea
    0.57
    <bos>
    0.56
    通販
    0.56
     mxArray
    0.56
    Attribution
    0.55
    אם
    0.55
     giusti
    0.55
    Activations Density 0.568%

    No Known Activations