© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14228
    Prev
    Next
    INDEX
    Explanations

    phrases indicating agreement between observations or predictions and prior work or simulations

    oai_token-act-pair · gemini-2.0-flash

    scientific agreement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     religieuses
    -0.71
     kesim
    -0.55
     militaires
    -0.53
     noastre
    -0.53
     prêtres
    -0.51
     armées
    -0.51
     culturelles
    -0.50
     noires
    -0.50
     rahasia
    -0.50
     vendus
    -0.49
    POSITIVE LOGITS
    WEBPACK
    0.65
    ГЛА
    0.62
     intptr
    0.60
    tangentMode
    0.59
     bê
    0.59
    IndentedString
    0.59
     peix
    0.58
    )";
    0.57
    brata
    0.57
    httphttps
    0.57
    Activations Density 2.283%

    No Known Activations