© 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. 14611
    Prev
    Next
    INDEX
    Explanations

    words and phrases relating to water and bodies of water

    oai_token-act-pair · gemini-2.0-flash

    water

    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
    endipity
    -0.48
    alho
    -0.46
    XmlRootElement
    -0.45
    ENZA
    -0.41
     med
    -0.41
     pos
    -0.41
     sn
    -0.41
    enst
    -0.41
    </tbody>
    -0.40
    ಂದ
    -0.40
    POSITIVE LOGITS
     water
    1.14
    Water
    1.05
     Water
    1.03
    water
    1.02
     Вода
    1.00
     watery
    0.98
     WATER
    0.97
     waters
    0.94
    WATER
    0.93
    RenderAtEndOf
    0.90
    Activations Density 1.362%

    No Known Activations