© 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. 13178
    Prev
    Next
    INDEX
    Explanations

    mentions of color in different contexts and descriptions.

    oai_token-act-pair · gemini-2.0-flash

    words related to colors and formatting

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

    Colors and descriptions

    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
     blue
    -1.67
     color
    -1.61
     purple
    -1.59
     yellow
    -1.59
     white
    -1.53
     colored
    -1.52
     colour
    -1.51
     green
    -1.47
     colors
    -1.45
     grey
    -1.45
    POSITIVE LOGITS
     Karten
    0.46
    ">—
    0.42
    ufen
    0.39
     muerta
    0.39
    CHEZ
    0.38
     conva
    0.38
    glBind
    0.37
     Bread
    0.37
    Bread
    0.37
    FormTagHelper
    0.37
    Activations Density 0.272%

    No Known Activations