© 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. 742
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to changes of state, modification, being, and how things were at a certain point in time.

    oai_token-act-pair · gemini-2.0-flash

    things being changed

    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
    Not in Any Lists

    No Comments

    Negative Logits
     illustrazione
    -0.54
    darah
    -0.53
     fondament
    -0.53
     fusca
    -0.50
     Zwiebel
    -0.49
    KeyId
    -0.49
     tén
    -0.48
     scio
    -0.48
     voluto
    -0.48
     piú
    -0.47
    POSITIVE LOGITS
    RenderAtEndOf
    0.81
    StoryboardSegue
    0.66
     initComponents
    0.60
     distributed
    0.58
     resourceCulture
    0.56
     متعلقه
    0.56
    LabelTagHelper
    0.54
    исленность
    0.54
    ništ
    0.52
     Italijanski
    0.52
    Activations Density 2.176%

    No Known Activations