© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4137
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "try" and its counterparts in related languages

    oai_token-act-pair · gemini-2.0-flash

    try

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     myſelf
    -1.09
     itſelf
    -1.02
     himſelf
    -0.93
     Jefus
    -0.92
     faſt
    -0.88
     pleaſure
    -0.87
     ſeveral
    -0.83
     themſelves
    -0.82
     Majefty
    -0.82
     occaf
    -0.81
    POSITIVE LOGITS
     attempt
    1.54
     attempts
    1.36
     Attempt
    1.35
     trying
    1.32
     attempting
    1.30
    attempt
    1.28
     attempted
    1.26
    Attempt
    1.22
     Trying
    1.21
    trying
    1.20
    Activations Density 0.554%

    No Known Activations