© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14778
    Prev
    Next
    INDEX
    Explanations

    the word "disc."

    oai_token-act-pair · gemini-2.0-flash

    disc

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     enfans
    -0.82
     habet
    -0.60
     creș
    -0.59
     démocr
    -0.57
     warunki
    -0.57
     tercio
    -0.57
     quæ
    -0.56
     chiare
    -0.56
     dieux
    -0.56
     Romains
    -0.56
    POSITIVE LOGITS
    henge
    0.74
    ChildScrollView
    0.73
     skimage
    0.72
    atorics
    0.65
    ClientRect
    0.65
     Wicidata
    0.64
    igslist
    0.63
    """)
    0.63
    hamdulillah
    0.63
     Мексичка
    0.62
    Activations Density 1.025%

    No Known Activations