© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12142
    Prev
    Next
    INDEX
    Explanations

    descriptions or statements of fame and achievements

    oai_token-act-pair · gemini-2.0-flash

    being known/famous

    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
     famous
    -1.91
    famous
    -1.73
     infamous
    -1.49
     famed
    -1.49
     Famous
    -1.48
    Famous
    -1.46
     famoso
    -1.40
     renowned
    -1.38
     iconic
    -1.34
     popular
    -1.34
    POSITIVE LOGITS
     Italijanski
    0.75
     متعلقه
    0.65
     AspNetCore
    0.59
     SqlParameter
    0.59
     lenker
    0.58
     utafitiHapana
    0.57
     doPost
    0.57
    MigrationBuilder
    0.56
    tonsoft
    0.55
    AnimationsModule
    0.55
    Activations Density 0.659%

    No Known Activations