© 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. 13385
    Prev
    Next
    INDEX
    Explanations

    language comparing or describing different varieties of products.

    oai_token-act-pair · gemini-2.0-flash

    design and color variations

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

    Design and color

    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
    ásra
    -0.66
    awtextra
    -0.61
     Theſe
    -0.59
    UnusedPrivate
    -0.58
     poffe
    -0.56
    gdx
    -0.55
    createCanvas
    -0.54
     endregion
    -0.54
    erees
    -0.53
    HasKey
    -0.53
    POSITIVE LOGITS
     design
    1.13
     color
    1.09
     colors
    1.04
     designs
    1.02
     colour
    0.98
     colours
    0.96
     styles
    0.90
    colors
    0.90
     sizes
    0.90
     colores
    0.89
    Activations Density 1.864%

    No Known Activations