© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12315
    Prev
    Next
    INDEX
    Explanations

    roman numerals and sometimes other capital letters and numbers in a variety of contexts

    oai_token-act-pair · gemini-2.0-flash

    Roman numerals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    IndentedString
    -0.71
    expandindo
    -0.64
     jspb
    -0.63
    ̍t
    -0.61
    "}")
    -0.61
    ttino
    -0.58
    /***/
    -0.57
    Билгалдахарш
    -0.57
    addContainerGap
    -0.56
    jspx
    -0.52
    POSITIVE LOGITS
     pleaſure
    0.55
    ſelf
    0.53
    Kedua
    0.53
     plonge
    0.52
     viceversa
    0.52
     ſmall
    0.51
    Сюжет
    0.50
     lópez
    0.49
     fevere
    0.49
     (!__
    0.48
    Activations Density 2.369%

    No Known Activations