© 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. 15415
    Prev
    Next
    INDEX
    Explanations

    mentions of brands, models, or property

    oai_token-act-pair · gemini-2.0-flash

    models and brands

    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
    GraphicsUnit
    -0.79
    ollectionView
    -0.74
     kasarigan
    -0.69
     المعيارى
    -0.65
     unknownFields
    -0.61
    processable
    -0.61
    parsedMessage
    -0.60
    Einzelnachweise
    -0.59
    OCCURRED
    -0.59
     otomatig
    -0.59
    POSITIVE LOGITS
     model
    0.70
     Model
    0.62
     models
    0.62
     name
    0.59
    model
    0.58
    name
    0.57
     modelo
    0.57
     modèles
    0.57
    Model
    0.57
    modelName
    0.54
    Activations Density 1.286%

    No Known Activations