© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13775
    Prev
    Next
    INDEX
    Explanations

    references to activities, mindset, and purpose of life

    oai_token-act-pair · gemini-2.0-flash

    life

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    belongsTo
    -0.49
    BindingResult
    -0.47
     Laus
    -0.45
     pau
    -0.43
     clearance
    -0.43
     comparison
    -0.42
     Murray
    -0.42
     testing
    -0.41
     بط
    -0.41
     cardia
    -0.40
    POSITIVE LOGITS
     initComponents
    0.86
    tagHelperRunner
    0.81
    +#+#
    0.81
    ItemBackground
    0.78
    InitVars
    0.73
     AssemblyCompany
    0.71
     kasarigan
    0.70
    getDescriptor
    0.69
     MainAxisSize
    0.64
     الحره
    0.63
    Activations Density 1.218%

    No Known Activations