© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15937
    Prev
    Next
    INDEX
    Explanations

    mentions of years, money, countries, and possibly other quantitative information

    oai_token-act-pair · gemini-2.0-flash

    1

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Ause
    -0.50
    ]<<
    -0.44
    Autoritní
    -0.42
    tanleria
    -0.41
    la
    -0.40
    NonNull
    -0.40
    styleable
    -0.40
    ]<<"
    -0.40
    trans
    -0.39
     entanto
    -0.38
    POSITIVE LOGITS
    enumi
    0.94
    ReusableCell
    0.77
    tvguidetime
    0.77
     IndexPath
    0.75
    devamını
    0.71
    ValueStyle
    0.71
    ADELPHIA
    0.68
    AutoresizingMask
    0.64
     للمعارف
    0.63
    queles
    0.62
    Activations Density 3.791%

    No Known Activations