© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7522
    Prev
    Next
    INDEX
    Explanations

    words related to beauty, cosmetics, and crafting

    oai_token-act-pair · gemini-2.0-flash

    products related to beauty and cosmetics

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

    shades

    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
    Passcode
    -0.65
    المكان
    -0.58
    LEncoder
    -0.57
     насељу
    -0.56
    TypedDataSet
    -0.56
    spesies
    -0.56
    Παραπομπές
    -0.56
     KPK
    -0.55
     fusca
    -0.55
    SpringBootTest
    -0.54
    POSITIVE LOGITS
     shades
    0.57
     shade
    0.57
     formula
    0.56
     chip
    0.55
     sm
    0.52
     she
    0.50
     bottle
    0.49
    sm
    0.49
    enumi
    0.49
     Kart
    0.49
    Activations Density 2.662%

    No Known Activations