© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12771
    Prev
    Next
    INDEX
    Explanations

    descriptive words related to design and fashion

    oai_token-act-pair · gemini-2.0-flash

    fashion and design

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    rungsseite
    -0.66
    ंदीखरीदारी
    -0.63
     pinulongan
    -0.62
    atians
    -0.61
     متعلقه
    -0.60
    rshire
    -0.60
    ctuaries
    -0.60
     financières
    -0.57
     grosso
    -0.57
     suprême
    -0.56
    POSITIVE LOGITS
    OGND
    0.62
    +#+#
    0.55
    новништво
    0.53
    essoal
    0.45
     stod
    0.44
     *:
    0.44
     BrowserModule
    0.43
     calm
    0.43
    indow
    0.42
    sober
    0.42
    Activations Density 1.095%

    No Known Activations