© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8857
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to painting, finishing, and weathering models.

    oai_token-act-pair · gemini-2.0-flash

    coats

    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
     незавершена
    -0.86
     peaking
    -0.65
     CreateTagHelper
    -0.59
    UnsafeEnabled
    -0.58
     تضيفلها
    -0.58
    kuuta
    -0.57
     femininas
    -0.57
    })*/
    -0.56
    ivably
    -0.56
    gnancy
    -0.55
    POSITIVE LOGITS
     coats
    0.66
    Coat
    0.61
    coat
    0.61
     Coats
    0.59
     coat
    0.57
     primer
    0.56
    coats
    0.52
     coatings
    0.51
     reco
    0.50
     sealer
    0.50
    Activations Density 1.050%

    No Known Activations