© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7237
    Prev
    Next
    INDEX
    Explanations

    words relating to surface properties, like roughness, wetting, and coating.

    oai_token-act-pair · gemini-2.0-flash

    slipperiness

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     فريبيس
    -0.84
    MemoryWarning
    -0.83
    onViewCreated
    -0.76
     دیکھیے
    -0.75
    +#+
    -0.73
     propOrder
    -0.73
    bootstrapcdn
    -0.71
     estekak
    -0.71
    StoryboardSegue
    -0.69
    ậc
    -0.69
    POSITIVE LOGITS
     slick
    0.66
     wet
    0.56
     slippery
    0.49
     oiled
    0.47
     oil
    0.46
     print
    0.46
    wet
    0.46
    Wet
    0.45
     lubric
    0.45
     Oil
    0.44
    Activations Density 1.332%

    No Known Activations