© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6821
    Prev
    Next
    INDEX
    Explanations

    words related to the water cycle, weather, and soil

    oai_token-act-pair · gemini-2.0-flash

    technical terms related to water and ecology

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

    water

    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
     genom
    -0.48
    TypedDataSet
    -0.47
    model
    -0.46
     mécan
    -0.46
    migrationBuilder
    -0.45
    ském
    -0.45
    esserung
    -0.44
     Sociales
    -0.43
     gentes
    -0.43
    objeto
    -0.43
    POSITIVE LOGITS
    ioutil
    0.77
    AttributeSet
    0.66
    AccessorTable
    0.63
    PyExc
    0.60
    hoeddwyd
    0.60
    setVerticalGroup
    0.59
     resourceCulture
    0.59
    prüche
    0.59
    bnf
    0.59
    참고
    0.57
    Activations Density 0.440%

    No Known Activations