© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14705
    Prev
    Next
    INDEX
    Explanations

    legal jargon, including references to courts, laws, and legal proceedings

    oai_token-act-pair · gemini-2.0-flash

    C

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     betweenstory
    -0.82
    Cyfarwyddwr
    -0.60
     للمعارف
    -0.60
    Geplaatst
    -0.58
     sī
    -0.58
    TagHelper
    -0.56
    ніципа
    -0.55
     "$@"
    -0.55
    ள்ள
    -0.52
     Ministro
    -0.52
    POSITIVE LOGITS
    tvguidetime
    0.69
    DOCTYPE
    0.58
    bootstrapcdn
    0.58
    styleable
    0.57
    usermodel
    0.54
     convertView
    0.52
    GraphicsUnit
    0.50
     createState
    0.50
    chromedriver
    0.50
    resave
    0.50
    Activations Density 12.388%

    No Known Activations