© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11158
    Prev
    Next
    INDEX
    Explanations

    code and documentation related to scatter plots

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
    findpost
    -1.02
    TagMode
    -0.88
    ValueStyle
    -0.87
    Gambas
    -0.85
    Vidite
    -0.83
    RectangleBorder
    -0.77
     تانيه
    -0.76
     препратки
    -0.76
     MainAxisSize
    -0.76
    Rhestr
    -0.75
    POSITIVE LOGITS
    ush
    0.45
     const
    0.44
    laf
    0.42
    USH
    0.41
    oo
    0.39
    )))
    0.39
     master
    0.39
     #
    0.38
     tra
    0.37
    меча
    0.37
    Activations Density 0.996%

    No Known Activations