© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12308
    Prev
    Next
    INDEX
    Explanations

    words that describe royalty, a game, or database locking, though not every time

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    %)$
    -0.53
    izoen
    -0.49
     NEC
    -0.49
    atschappij
    -0.47
    brigens
    -0.44
     ProtoMessage
    -0.43
    covo
    -0.43
    '));
    -0.42
     touche
    -0.42
    makeText
    -0.42
    POSITIVE LOGITS
    Revenir
    0.71
    afficheront
    0.67
     BoxFit
    0.60
    Hochspringen
    0.60
    ArgsConstructor
    0.60
    شهاد
    0.59
    ContentAsync
    0.57
    titleMargin
    0.57
    StandardCharsets
    0.56
    TargetException
    0.55
    Activations Density 3.822%

    No Known Activations