© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5966
    Prev
    Next
    INDEX
    Explanations

    language related to cosmetic procedures and anti-aging treatments like Botox and dermal fillers.

    oai_token-act-pair · gemini-2.0-flash

    botox and dermal fillers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    dere
    -0.47
    ParallelGroup
    -0.46
    Capítulo
    -0.44
    kenal
    -0.44
     PRIVATE
    -0.42
    HISTORIA
    -0.42
    criminate
    -0.42
    abetta
    -0.41
    ệ
    -0.41
     quarto
    -0.41
    POSITIVE LOGITS
     betweenstory
    0.77
     ExecuteAsync
    0.74
     GenerationType
    0.71
     nahilalakip
    0.69
     kasarigan
    0.67
    MessageTagHelper
    0.63
     Fill
    0.63
     vuitton
    0.62
    \{\\
    0.62
    PreferredItem
    0.61
    Activations Density 2.189%

    No Known Activations