© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10470
    Prev
    Next
    INDEX
    Explanations

    text that is associated with Bollywood style or Indian names

    oai_token-act-pair · gemini-2.0-flash

    design

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    +#+#
    -0.83
    SourceChecksum
    -0.77
     &___
    -0.75
     <=",
    -0.75
     ExecuteAsync
    -0.74
    windowFixed
    -0.69
    parsedMessage
    -0.69
     Exacts
    -0.68
     للاسماء
    -0.65
    الإنجليزية
    -0.65
    POSITIVE LOGITS
    Design
    0.67
     Designer
    0.64
     Design
    0.64
     designers
    0.63
     Designers
    0.62
     DESIGN
    0.62
    design
    0.62
     esterni
    0.61
     design
    0.61
     Liabilities
    0.57
    Activations Density 1.899%

    No Known Activations