© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13914
    Prev
    Next
    INDEX
    Explanations

    text that has to do with research study methodology, including samples, data, and health/social behaviors.

    oai_token-act-pair · gemini-2.0-flash

    Operation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     AssemblyCulture
    -0.64
    Referanser
    -0.51
    chaub
    -0.49
    ollectionView
    -0.48
     собой
    -0.47
    dorff
    -0.47
    vieja
    -0.46
    Hentet
    -0.46
     disponibilités
    -0.46
    StoryboardSegue
    -0.45
    POSITIVE LOGITS
     Operation
    0.63
     operational
    0.62
     Operational
    0.60
     operation
    0.58
    Operation
    0.58
    GeneratedCode
    0.58
    AnchorStyles
    0.57
     operacional
    0.56
    Климат
    0.56
    Coding
    0.56
    Activations Density 5.429%

    No Known Activations