© 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. 3345
    Prev
    Next
    INDEX
    Explanations

    words related to the act of creating or installing things, in specific technical contexts, but with some false positives

    oai_token-act-pair · gemini-2.0-flash

    installation/formation

    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
     creation
    -1.15
     installation
    -1.09
     implementation
    -0.97
     formation
    -0.97
     $_"
    -0.95
    creation
    -0.90
     publication
    -0.88
    installation
    -0.88
     establishment
    -0.85
     completion
    -0.84
    POSITIVE LOGITS
    EUROPA
    0.74
     Giuliani
    0.73
     Bourgoin
    0.73
    énario
    0.71
    Politik
    0.71
     CreateTagHelper
    0.69
    RegressionTest
    0.68
     تضيفلها
    0.68
    Diwedd
    0.67
    Scénario
    0.66
    Activations Density 5.405%

    No Known Activations