© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12254
    Prev
    Next
    INDEX
    Explanations

    certain everyday objects

    oai_token-act-pair · gemini-2.0-flash

    everyday objects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    CppMethod
    -0.88
    IContainer
    -0.86
     utafitiHapana
    -0.69
    LLocation
    -0.69
    Tembelea
    -0.68
     مرئيه
    -0.66
    sizeCache
    -0.65
    >{@
    -0.65
    enterOuterAlt
    -0.65
    RTEE
    -0.65
    POSITIVE LOGITS
     Reihen
    0.44
    ynı
    0.43
     bestellen
    0.41
     perfectos
    0.39
     correcta
    0.39
     JUGA
    0.39
    PRNewswire
    0.39
    racite
    0.37
     ")[
    0.37
    кладки
    0.36
    Activations Density 1.279%

    No Known Activations