© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10091
    Prev
    Next
    INDEX
    Explanations

    mostly whitespace, but also a very eclectic mix of seemingly random characters and words

    oai_token-act-pair · gemini-2.0-flash

    mathematical equations/code

    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
     esternos
    -0.78
     estimés
    -0.57
    Filmografia
    -0.57
     propOrder
    -0.56
    latego
    -0.54
     homosexuality
    -0.52
    RegistryLite
    -0.52
    tinggi
    -0.52
    Slf
    -0.51
    meadow
    -0.50
    POSITIVE LOGITS
    Халык
    0.59
     समीक्षक
    0.56
    gestellt
    0.56
    っこう
    0.55
    HasForeignKey
    0.55
     configureStore
    0.54
    GenerationType
    0.53
     getItemId
    0.52
    interopRequire
    0.51
     Normdatei
    0.50
    Activations Density 3.951%

    No Known Activations