© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10751
    Prev
    Next
    INDEX
    Explanations

    labels and numbers, sometimes related to scientific vocabulary

    oai_token-act-pair · gemini-2.0-flash

    6

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    +#+#
    -0.82
     Efq
    -0.75
    runApp
    -0.71
    ::_('
    -0.71
     photolibrary
    -0.68
    ècie
    -0.67
     pitié
    -0.67
     itſelf
    -0.66
     محفوظة
    -0.66
     ་་
    -0.66
    POSITIVE LOGITS
    6
    0.51
    PYX
    0.50
     poverty
    0.50
     Six
    0.49
     инжен
    0.48
    tadır
    0.47
     sou
    0.47
     Parti
    0.46
    GroupLayout
    0.46
    AddAttribute
    0.46
    Activations Density 2.301%

    No Known Activations