© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6000
    Prev
    Next
    INDEX
    Explanations

    words related to conversations regarding policies and issues

    oai_token-act-pair · gemini-2.0-flash

    discussion

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     purpoſe
    -0.73
    addMessage
    -0.64
     uſe
    -0.63
    MLLoader
    -0.62
     Chriftian
    -0.62
     fhew
    -0.61
     themſelves
    -0.60
     Conſ
    -0.59
     ſtate
    -0.59
    gridy
    -0.58
    POSITIVE LOGITS
    neté
    0.54
    SharedDtor
    0.53
     referrerpolicy
    0.51
    ########.
    0.48
     viewDidLoad
    0.46
    スカ
    0.46
    saraba
    0.45
    ẳng
    0.45
     about
    0.43
    ————————————
    0.43
    Activations Density 4.194%

    No Known Activations