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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12270
    Prev
    Next
    INDEX
    Explanations

    words related to colors and design choices

    oai_token-act-pair · gemini-2.0-flash

    Colors and patterns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Colour
    -0.77
    Color
    -0.72
     Color
    -0.72
    ContentAsync
    -0.72
     colour
    -0.71
     color
    -0.69
    Colour
    -0.69
     Colors
    -0.68
     COLOR
    -0.66
     Colours
    -0.66
    POSITIVE LOGITS
    новниш
    0.67
    Personendaten
    0.60
     jadx
    0.60
     p
    0.59
    kháu
    0.55
    المشاركات
    0.54
    Jereo
    0.50
    ///</
    0.49
     PublicKey
    0.49
     تعدى
    0.49
    Activations Density 4.780%

    No Known Activations