© 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. 10919
    Prev
    Next
    INDEX
    Explanations

    the string 'tr' or 'TR', sometimes followed by other characters

    oai_token-act-pair · gemini-2.0-flash

    tr

    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
     שוליים
    -0.62
     CURIAM
    -0.53
    Parameterized
    -0.52
    ive
    -0.49
     Sab
    -0.48
    KommentareTeilen
    -0.48
     Camp
    -0.46
     sels
    -0.46
     архивлан
    -0.46
    ydd
    -0.46
    POSITIVE LOGITS
     Efq
    0.79
     myſelf
    0.78
     uſed
    0.74
     himſelf
    0.73
     themſelves
    0.73
    Portale
    0.72
     Jefus
    0.71
     itſelf
    0.71
     ſeveral
    0.69
     theſe
    0.68
    Activations Density 0.701%

    No Known Activations