© 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. 15485
    Prev
    Next
    INDEX
    Explanations

    words that have the suffix "ed", words related to government and other social concepts, and words related to marketing.

    oai_token-act-pair · gemini-2.0-flash

    some

    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
     thereto
    -0.81
    ########.
    -0.61
    tothe
    -0.58
    ༘
    -0.57
    CopyWith
    -0.57
    Datuak
    -0.57
    Bronnen
    -0.53
    Personensuche
    -0.52
     chi̍t
    -0.52
    axx
    -0.52
    POSITIVE LOGITS
    Espèce
    0.65
    出版年
    0.59
    tamide
    0.50
     personalización
    0.48
    uat
    0.48
    ArrayType
    0.48
    OffsetY
    0.47
    IsPostBack
    0.47
    ussis
    0.47
     francès
    0.46
    Activations Density 46.352%

    No Known Activations