© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1580
    Prev
    Next
    INDEX
    Explanations

    descriptions of people's attire

    oai_token-act-pair · gemini-2.0-flash

    clothing descriptors

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

    Protective clothing or gear

    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
    Negative Logits
     wear
    -0.91
     wears
    -0.85
    wear
    -0.84
     Wear
    -0.83
     wearing
    -0.82
    Wearing
    -0.82
     wore
    -0.82
    wearing
    -0.81
    Wear
    -0.81
     Wearing
    -0.81
    POSITIVE LOGITS
    SourceChecksum
    0.79
    KURZBESCHREIBUNG
    0.65
    }{*}{}
    0.61
    ########.
    0.60
     onPostExecute
    0.59
    WriteTagHelper
    0.55
     NavController
    0.53
    Hentet
    0.53
    knex
    0.52
    cipar
    0.52
    Activations Density 0.337%

    No Known Activations