© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9670
    Prev
    Next
    INDEX
    Explanations

    descriptive words related to nature, especially colors and beauty

    oai_token-act-pair · gemini-2.0-flash

    colors related to nature

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

    color green

    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
    endpush
    -0.63
    RectangleBorder
    -0.57
     endblock
    -0.54
    createNewFile
    -0.51
    setlength
    -0.48
    Дереккөздер
    -0.46
    原始内容存档于
    -0.46
    JNIEnv
    -0.45
    setTypeface
    -0.45
    nonatomic
    -0.43
    POSITIVE LOGITS
     green
    1.26
     color
    1.15
     colors
    1.14
    green
    1.13
     colored
    1.11
     colour
    1.09
     colours
    1.04
     coloring
    1.02
     yellow
    1.02
     Green
    1.02
    Activations Density 1.854%

    No Known Activations