© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5724
    Prev
    Next
    INDEX
    Explanations

    the word "editor" and words associated with newspapers

    oai_token-act-pair · gemini-2.0-flash

    editor

    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
     the
    -1.00
     in
    -0.69
     all
    -0.68
    s
    -0.66
     it
    -0.66
     various
    -0.66
     other
    -0.65
     complete
    -0.62
     to
    -0.60
     this
    -0.59
    POSITIVE LOGITS
     nakalista
    1.47
    rungsseite
    1.38
    RegressionTest
    1.29
     CreateTagHelper
    1.27
    :✨
    1.26
    Personendaten
    1.19
    verwijspagina
    1.16
     kaarangay
    1.16
    цездатний
    1.16
     Roskov
    1.13
    Activations Density 1.507%

    No Known Activations