© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10715
    Prev
    Next
    INDEX
    Explanations

    words related to fire disasters and also the process of burning things.

    oai_token-act-pair · gemini-2.0-flash

    fire-related terms

    np_token-act-pair-logits · gpt-4o-mini

    light/lighting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     ExecuteAsync
    -0.56
    OrNil
    -0.54
     estimés
    -0.49
    sy
    -0.49
    Personendaten
    -0.48
    SY
    -0.45
     Réponses
    -0.44
     Wicidata
    -0.44
     invokingState
    -0.44
    ylle
    -0.43
    POSITIVE LOGITS
     lighting
    0.81
    ItemBackground
    0.81
     matches
    0.75
    lighting
    0.73
     match
    0.71
     fire
    0.69
    lights
    0.68
     light
    0.68
     ligh
    0.68
    match
    0.67
    Activations Density 2.155%

    No Known Activations