© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9292
    Prev
    Next
    INDEX
    Explanations

    words frequently found in product descriptions or tutorials for cosmetic procedures designed to alter one's appearance.

    oai_token-act-pair · gemini-2.0-flash

    plump

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     oprot
    -0.63
    uxxxx
    -0.56
     neutral
    -0.54
    ERY
    -0.53
    cery
    -0.52
    createStatement
    -0.51
    ivity
    -0.51
    RTRS
    -0.51
    timo
    -0.51
    timate
    -0.51
    POSITIVE LOGITS
    SceneManagement
    0.66
     HasFactory
    0.60
    kloped
    0.59
    webElementXpaths
    0.58
    Viited
    0.55
    Bioaccumulative
    0.54
    PyExc
    0.54
    slidesToShow
    0.53
    Cyfeiriadau
    0.53
    ="@+
    0.53
    Activations Density 1.174%

    No Known Activations