© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10428
    Prev
    Next
    INDEX
    Explanations

    words relating to differences, changes, or things that can vary

    oai_token-act-pair · gemini-2.0-flash

    variable

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    protoimpl
    -0.74
    MessageTagHelper
    -0.73
     متعلقه
    -0.73
    yntaxException
    -0.72
    cèse
    -0.72
    findpost
    -0.70
     NSCoder
    -0.69
    OGND
    -0.69
    addContainerGap
    -0.69
     BoxFit
    -0.68
    POSITIVE LOGITS
     Mangel
    0.47
    Viewed
    0.44
    push
    0.43
     LCCN
    0.42
     tío
    0.42
    send
    0.42
     surn
    0.41
     LUMP
    0.41
     getContent
    0.41
     zdan
    0.40
    Activations Density 9.169%

    No Known Activations