© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5480
    Prev
    Next
    INDEX
    Explanations

    language from scientific papers that describe observations on multiple interacting factors

    oai_token-act-pair · gemini-2.0-flash

    interaction

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     unknownFields
    -0.71
    XmlAccessType
    -0.59
    OKA
    -0.56
     ComVisible
    -0.56
    afficheront
    -0.54
     Pilipinas
    -0.53
    expandindo
    -0.52
    帖最后由
    -0.50
    IVEREF
    -0.49
     EconPapers
    -0.49
    POSITIVE LOGITS
     interaction
    1.57
     interactions
    1.52
     Interactions
    1.46
    interaction
    1.38
     Interaction
    1.35
     interact
    1.34
    Interactions
    1.33
    Interaction
    1.27
     interacts
    1.23
    interactions
    1.20
    Activations Density 2.881%

    No Known Activations