© 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. 12954
    Prev
    Next
    INDEX
    Explanations

    general words that don't carry too much specific information.

    oai_token-act-pair · 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
    GEBURTSDATUM
    -0.81
     propOrder
    -0.79
    +#+#
    -0.64
     <=",
    -0.61
    ConstraintMaker
    -0.60
    makeConstraints
    -0.59
     استنادى
    -0.56
    everything
    -0.55
     morire
    -0.55
    InitVars
    -0.55
    POSITIVE LOGITS
    waitKey
    0.52
     nghĩ
    0.51
    usda
    0.49
     post
    0.49
    PutMapping
    0.48
    WebMethod
    0.48
    Supply
    0.48
    ="#"><
    0.48
     Fool
    0.47
    essayer
    0.47
    Activations Density 5.179%

    No Known Activations