© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 6710
    Prev
    Next
    INDEX
    Explanations

    replace, replaced, replacing, replacement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wait
    0.31
     waits
    0.30
     WAIT
    0.30
    Wait
    0.29
     ждать
    0.29
     trattamento
    0.28
     Wait
    0.28
    待
    0.28
     기다
    0.27
     tratamiento
    0.27
    POSITIVE LOGITS
     replace
    0.88
    replace
    0.88
     replaced
    0.86
    Replace
    0.84
     replacement
    0.84
     replacing
    0.82
     Replace
    0.80
     replaces
    0.78
     Replacement
    0.78
    replacement
    0.77
    Activations Density 0.036%

    No Known Activations