© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6344
    Prev
    Next
    INDEX
    Explanations

    mentions of lights, especially LED and traffic lights

    oai_token-act-pair · gemini-2.0-flash

    lights

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     lights
    -2.42
     Lights
    -2.14
     lighting
    -2.03
     LIGHTS
    -2.02
    lights
    -2.02
    Lights
    -2.02
     Lighting
    -1.95
    Lighting
    -1.83
    lighting
    -1.65
    LIGHTS
    -1.62
    POSITIVE LOGITS
    SequentialGroup
    0.59
    éez
    0.52
    AndEndTag
    0.51
    Erstellt
    0.50
    preventDefault
    0.49
    getDescriptor
    0.47
    RenderAtEndOf
    0.45
     Brah
    0.44
    тельств
    0.44
    neuf
    0.44
    Activations Density 0.670%

    No Known Activations