© 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. 11269
    Prev
    Next
    INDEX
    Explanations

    the word "le" or "Le", sometimes near the word "laisse"

    oai_token-act-pair · gemini-2.0-flash

    le

    np_max-act · gemini-2.0-flash

    Le

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    Le
    -1.71
     le
    -1.64
     Le
    -1.63
     LE
    -1.51
    le
    -1.48
    LE
    -1.47
     Ле
    -1.08
     Lea
    -1.02
    Lea
    -1.00
    leis
    -0.97
    POSITIVE LOGITS
    KEYCODE
    0.64
    VolleyError
    0.55
    Viited
    0.51
    esgue
    0.49
    GrantedAuthority
    0.49
    $_['
    0.47
    #
    0.46
    مراجع
    0.46
     архивлан
    0.45
    مصادر
    0.45
    Activations Density 1.056%

    No Known Activations